Skip to main content
Glama
FeatureBoard MCP Server

FeatureBoard MCP Server

by valentil

FeatureBoard — the board Claude actually runs

A local, markdown-backed project board that lives inside Claude — packaged as a Claude Desktop / Cowork extension (.mcpb). Point it at a folder, and Claude plans, logs, prioritizes, and works tickets in plain language — then renders the whole thing as a live, interactive board artifact with a full analytics dashboard. No SaaS, no login, no lock-in. Your boards are plain featurelist.md / buglist.md files you own forever.

It started as a hosted web app (OpenClaw). We rebuilt it as an MCP server by taking the original app's file list and porting it, tool by tool, while learning MCP from scratch — and it came together fast. What you get is ~216 tools spanning the entire product surface: board and churn loop, analytics, testing, a media studio, CRM, leads, contracts, mail and marketing, a website builder with git deploys, and per-ticket commits. The board is the front door; everything the original app did is one sentence away in chat.

Why it's good

  • It's the board Claude drives, not a database you poke. Ask "what's on my plate," "break FBF-300 into subtasks," or "ship the next ticket" — Claude pulls work, sets status, writes the code, logs the diff, and commits. The board stays honest because the agent keeps it honest.

  • One command opens the real UI. get_board returns the shipped board as a Cowork artifact — Todo / In Progress / Done columns, filters, dark mode, click-to-move, and a 📊 analytics dashboard (velocity, timeline, bug health, work-log feed) — all wired live to the server. No hand-rolled mockups.

  • Your files, your rules. Boards are byte-compatible markdown. Existing FeatureBoard folders work with zero migration. Writes are atomic. Delete the extension tomorrow and your boards are still just markdown.

  • Depth when you want it. The same server that tracks tickets also generates media, runs a CRM, drafts contracts and campaigns, builds and deploys a marketing site, and commits your code per ticket. Turn it down to the essentials with one toggle, or open the whole toolbox.

Related MCP server: kanban-mcp

Measured: what the board actually buys you

A paired agent trial (n=10, sonnet model tier) showed the work packet cuts diff churn 1.76x (837 vs 1,471 additions) with equal correctness (10/10 both). Token spend is 6–11% lower (77.5k vs 83.2k median), secondary to the focus gain: less to review, maintain, and scope drift on open-ended asks. See docs/EVAL-BOARD-VS-CHAT.md.

Quickstart

  1. Install the extension: double-click featureboard-0.9.2.mcpb, or Claude Desktop → Settings → Extensions → Advanced → Install Extension.

  2. On first run it asks for your Boards folder. Each subfolder with a featurelist.md or buglist.md is a board.

  3. Say "open the FeatureBoard board" — the live board opens as an artifact. Then just talk:

    • "Log a bug: gallery modal won't dismiss on mouse-out."

    • "Brainstorm five onboarding features and add them."

    • "Move FBF-207 to done — fixed the parser regex."

    • "How's velocity looking this week?"

First-run tip: the extension defaults to Essential tools only (~34 core board tools) for a clean start. Turn that off in the extension settings to expose the full ~216-tool surface (CRM, media, website, marketing, and more). After installing or updating, fully restart Claude Desktop so new tools load.

Not using Claude? Cursor, Grok Build, and any other MCP client can run the same server over stdio — see docs/INSTALL-OTHER-IDES.md for per-IDE config, tool-count limits, and the IDE-neutral instructions flag.

Recipes

Automate your board's daily routines without a daemon. Copy-paste these prompts into Claude Code → Scheduled tasks to run nightly board health checks, weekly sprint close-outs, and daily standups. See docs/RECIPES.md for three ready-to-use scheduled task recipes and tool reference.

Everything it can do

Board & tickets — list_projects · create_project · list_tasks · get_task · add_feature · log_bug · add_features_bulk · import_tasks · validate_feedback · plan_work · update_task · set_status · decompose_feature · link_tasks · add_attachment · remove_attachment · delete_task · add_product · remove_product · get_project_config · set_project_config · get_ticket_history

The live board — get_board (returns artifact/board.html, ready to render as a Cowork artifact — this is what "open/show the board" calls)

Churn loop & orchestration — next_task · get_work_packet · log_work · get_agent_monitor · get_scratchpad · set_scratchpad · append_scratchpad (pull one ticket, assemble a focused brief, dispatch to a sub-agent, record the diff, repeat. get_agent_monitor is the live view of what's In Progress right now: elapsed time since each ticket started, its last event with age, token spend vs its cap:<tokens> label, and a stalled flag — an inactivity threshold, 30min by default. Stalled tickets also surface as a warning banner on the board, useful for keeping an eye on an unattended churn run. It also reports costSoFar/ capCost in dollars — see cost tracking below.)

Knowledge base — add_kb_doc · list_kb_docs · get_kb_doc · search_kb (a per-project kb/ folder of markdown docs, beyond the scratchpad — keyword-matched into get_work_packet's kbMatches automatically). rag_search is the retrieval layer over kb + repo docs + Done-ticket summaries: BM25 always, and HYBRID (BM25 + local MiniLM embeddings via the optional @xenova/transformers dep, reciprocal-rank fusion) when installed — the ~25MB model downloads once on first use then runs offline forever; without it, pure lexical, zero network.

Audit timeline — get_ticket_history (per-ticket chronological log: set_status/ update_task/assign_sprint append status, priority, label, sprint, and due-date change events to ticket_events.jsonl; get_ticket_history merges those with the ticket's work-log entries into one view. Tickets from before this existed just show their work-log history. The board's 🕘 button on each card renders the same timeline.)

Code review — get_ticket_diff captures the code a ticket produced (finds commits mentioning the ticket id in the project's code repo and returns per-commit summaries plus size-capped unified diffs from git show). add_review_comment leaves PR-style feedback on a ticket (optionally anchored to a file/line); list_review_comments and resolve_review_comment manage it. Unresolved comments surface in the ticket's next work packet (get_work_packet.reviewComments) so the next agent acts on the feedback, and a comment on a ticket in Review sends it back into next_task's queue — otherwise tickets awaiting review are held out of next_task (they belong to the reviewer). The board's 🕘 ticket panel lists review comments with their resolved state.

Analytics & health — get_metrics · get_health · get_work_log · predict_due_dates (get_metrics's velocity section rolls up $ cost by model too, alongside tokens. Cost tracking is model-aware: server/pricing.js ships defaults sourced from current Anthropic API pricing — input/output $/MTok per model tier (fable/opus/sonnet/haiku) — and every rate is overridable per project via set_project_config's pricing key, so a stale default is harmless. Work-log entries with an inputTokens/outputTokens split are priced exactly; older entries with only a tokens total fall back to a blended rate. get_agent_monitor and eval_report roll up the same $ figures per ticket/arm, and the board's metrics panel shows a cost line with a per-model breakdown.)

Timeline (piano roll) — get_timeline_data (FBMCPF-158). The board's 🎹 Timeline panel is an Ableton-style piano roll: every ticket is a clip on a horizontal lane, spanning its worked window (created → In Progress → completed, from ticket_events.jsonl with a completion-day fallback). Lanes group by product / model / type / sprint / status; a sticky time ruler adapts its granularity (hour / day / week / sprint); wheel zooms centred on the pointer, shift+wheel or grab-drag pans. A single datastream overlay (tokens / cost / additions+deletions) draws as a strip under the ruler. Hover a clip for a compact card (title, status, model, tokens); click to pin an expanded card that lazily pulls get_ticket_history for selectable cost / status-history / work-log fields.

Sprint close-out reports — close_sprint · get_sprint_report (FBMCPF-156) (close a sprint and turn its tickets + work log + metrics into four audience-specific reports — marketing (features shipped, positioning-ready copy), sales (customer-facing capabilities + the CRM tickets they resolve), technical (per-ticket changes, commits, ADRs touched), and executive (velocity, spend vs budget, health, risks). close_sprint refuses to close while a sprint still has open tickets unless force:true (open ones are then reported as carryover), writes deterministic reports/<sprint>/<audience>.md pads under the project (byte-stable, no model calls), and also returns a per-audience LLM prompt — the report packet as JSON plus an audience brief — so an agent can draft richer copy while staying grounded in real data. When the project has Slack configured it posts a one-block summary on close (a Slack failure is reported, never fails the close). get_sprint_report reads them back: no sprint → list sprints with reports; a sprint → its manifest and which audiences exist; sprint + audience → that report's markdown. The board's 📄 Reports panel lists every sprint with reports and renders each audience in its own tab.)

Board hygiene — scan_board_cleanup · prune_board (also lints open tickets missing a model:/cap: label — see intake orchestration guard below)

Intake orchestration guard (FBMCPF-159) — every ticket-creating tool (add_feature, add_features_bulk, log_bug, plan_work, import_tasks, validate_feedback in apply mode, and report_company_bug) fills in a model:/cap: label at intake whenever the creator didn't set one, via server/orchestration.js's deterministic type/keyword/product heuristics (bug vs. feature, docs/copy/rename → haiku or sonnet, architecture/UI-heavy/multi-file/parity → opus, conservative default sonnet + cap:80000). It never overrides a model:/cap: label you set yourself — only fills in what's missing. scan_board_cleanup then lints for any open ticket that still slipped through without one.

Code awareness — list_code_files · read_code_file · code_file_map

Testing & QA — suggest_test_stub · generate_test · generate_multi_model_tests · save_generated_test · list_test_variants · eval_model_matrix · bug_impact_scan · log_test_run · get_test_runs · test_runs_by_suite · get_regressions · save_test_page · list_test_pages · get_test_page · remove_test_page (multi-model generation fans one test prompt across model tiers — fable/opus/sonnet — then dedupes overlapping assertions so each bug gets one variant per model in the suite; eval_model_matrix is the empirical follow-up (FBMCPF-148) — it runs each tier's variant file against seeded, deterministic mutations of the target source in a temp dir (never the repo) and reports per-model defect-catch rate, unique catches, an overlap matrix, and cost per caught defect, to inform when downgrading test generation to a cheaper tier is safe)

Drift (ticket-vs-code fidelity) — drift_start · drift_record · drift_report · drift_remediate (score how well the code matches the ticket, report, and auto-remediate)

Media studio — save_media · list_media · get_media · edit_media · list_variations · revert_media · tag_media · annotate_media · remove_annotation · search_media · add_media_comment · list_media_comments · remove_media_comment · upload_reference · list_references · publish_media_to_site · draft_share · list_shares · remove_share

CRM & customers — add_company · list_companies · get_company · add_contact · add_crm_message · submit_crm_intake · list_crm_inbox · review_crm_message · customer_portal · link_customer_ticket · unlink_customer_ticket · ticket_customers · add_company_agreement · update_company_agreement · remove_company_agreement

Leads & field sales — add_lead · list_leads · set_lead_status · enrich_lead · convert_lead · leads_map · add_lead_area · list_lead_areas · add_lead_interaction · update_lead_location

Contracts — list_contract_templates · generate_contract

Mail & marketing — draft_email · list_mail · get_email · mark_email_sent · create_campaign · list_campaigns · get_campaign · record_campaign_open

Bookings — book_meeting · cancel_booking · list_bookings

Website builder + deploy — get_site · set_site · scaffold_site · edit_site_section · add_page · list_pages · remove_page · deploy_site · upload_site_asset · list_site_assets · set_site_analytics · set_analytics_config · auto_configure_analytics · get_site_traffic · enable_login_gate · disable_login_gate

Per-ticket git — get_git_config · set_git_config · commit_feature

Packaging — suggest_packaging · save_packaging_config · validate_packaging

Licensing — license_status · set_usage_type · activate_license · request_commercial_license · register_email

list_tasks is paginated and compact by default (limit, offset, compact:false) so large boards never blow the context budget. Write tools echo the exact post-write line. Tickets can carry an external ref (e.g. a plan item WI-1.2). See DESIGN.md for what was ported from the original app and what was intentionally left out.

The live board (Cowork artifact)

artifact/board.html is a self-contained Kanban that renders any board through the tools above — columns, cards with due dates / products / labels / refs, click-to-move status, a metrics strip, dark/light theme, and the 📊 analytics dashboard. get_board hands it to Claude ready for create_artifact, so any natural-language "open the board" surfaces the real UI (not a reinvented one) and refreshes from the server every time it opens.

Per-ticket git integration (optional)

FeatureBoard can commit — and optionally push — your code repo per finished ticket, exactly like the original app did. It's opt-in, off by default, and stores no secrets: pushing uses your machine's own git credentials (credential manager / SSH), just like running git yourself.

set_git_config     project=MyApp enabled=true branch=main push=true
set_project_config project=MyApp codeLocation="/path/to/repo"
commit_feature     project=MyApp ticket=FBF-42 title="Login flow"
#   → git add . && git commit -m "FBF-42: Login flow" && git push origin main

get_git_config shows current settings; commit_feature no-ops with a clear reason when disabled. Config lives in the board's git.config.json.

Pad mirror on close-out (graduated projects). Once a project's stage is graduated (see graduate_project), commit_feature and set_status ... Done also refresh a read-only snapshot of the pad — featurelist.md, buglist.md, scratchpad.md, agent_work_log.md, and config — into <codeRepo>/.featureboard/. commit_feature stages and includes the snapshot in the same commit as the code change; set_status Done refreshes it on disk even if commit_feature isn't called for that ticket. The central pad stays authoritative — this is a one-way snapshot, so cloning the code repo gets you the code plus the board history that shipped with it. Missing pad files are skipped; a mirror failure is reported as a warning and never blocks the commit or the status change.

Parallel dispatch in isolated git worktrees (optional)

For Cline-Kanban-style parallel agents, FeatureBoard can give each ticket its own git worktree — a separate checked-out directory on its own branch (ticket/<ticket>) that shares the repo's .git object store. N sub-agents can then work N tickets at once, each editing its own directory instead of fighting over one working tree, and you merge the branches back serially.

create_worktree  project=MyApp ticket=FBF-42          # -> <codeLocation>-worktrees/FBF-42 on branch ticket/FBF-42
list_worktrees   project=MyApp
cleanup_worktree project=MyApp ticket=FBF-42          # after the branch is merged back (refuses if dirty; force to override)

When a worktree exists for a ticket, get_work_packet includes a worktree block (path, branch, and step-by-step merge-back guidance) so the dispatched sub-agent edits there, never the shared repo. Board writes stay orchestrator-only, and branches merge back serially (checkout the base branch, merge/rebase ticket/<id>, run tests, commit_feature, then cleanup_worktree).

⚠️ Sync caveat — worktrees live OUTSIDE the code repo. Under Cowork, the host↔sandbox folder sync interacts badly with git's internal worktree administration files: a worktree created inside a synced repo mount can corrupt git internals or fail to sync. So worktrees default to a sibling directory <codeLocation>-worktrees/ (outside the repo), configurable with the project config key worktreeDir. create_worktree refuses a worktreeDir inside the repo and never auto-creates worktrees in the repo itself. Point worktreeDir at a path outside every synced mount (e.g. an OS tmpdir) if in doubt.

5-minute quickstart

  1. Install: Claude Desktop -> Settings -> Extensions -> Install from file -> featureboard-mcp.mcpb. Restart Claude Desktop.

  2. Approve tools once: Settings -> Extensions -> FeatureBoard -> Tool permissions -> Allow all (see next section).

  3. Onboard: say "show my featureboard" — pick a license tier on the onboarding screen.

  4. Plan: paste: "Plan work for project MyApp: create it and add tickets for " — plan_work files everything with model/cap labels.

  5. Churn: say "work the board" — Claude pulls next_task, implements, commits, and closes tickets one at a time.

  6. Review: "show the board" for the live Kanban; "close the sprint" for an audience-ready report.

That's the whole loop. Everything below is depth.

One-time setup: approve tools in bulk

FeatureBoard registers ~195 tools. In Claude Desktop, open Settings → Extensions → FeatureBoard → Tool permissions and choose Allow all for read and write once, instead of approving each tool the first time it fires — per-tool prompts stall agent churn loops mid-run. The onboarding screen reminds you of this on first use.

Licensing

FeatureBoard is source-available (see LICENSE.md): free for private non-commercial and public/nonprofit use (PolyForm Noncommercial), with a free 24-hour commercial trial after which write tools freeze (reads keep working) until a commercial key is activated. Commercial keys are US$99.99/seat/year (or US$9.99/seat/month), self-serve at https://featureboard.ai/buy. Activate with activate_license in either mode: paste the key itself, or pass the email + order id from your Polar purchase receipt and the server fetches the signed key for you from the featureboard.ai claim API — no copy-pasting a key required. You can also retrieve a key manually anytime with that same email + order id at https://featureboard.ai/claim and paste it in yourself. The board UI's "Activate license key" screen offers both paths side by side. On first use, onboarding asks which tier applies. Owners issue keys with the offline generator in owner/ (never shipped — .mcpbignore excludes it); see owner/README.md for the request → contract → issue-key → customer flow.

The same onboarding screen has an optional email field. Nothing is stored or sent unless you explicitly click "Save email" — that click is the only consent signal used. On submit, the email is saved locally and POSTed once to the featureboard.ai registrations listener; skip the field and it never leaves your machine.

FeatureBoard also collects anonymous usage telemetry: per-day counts of which of its own tools were called (names only — never arguments, results, or board content), batched to featureboard.ai at most once per 24h under a random install id that is never joined to your email. Opt out anytime with FEATUREBOARD_TELEMETRY=0 in the environment or set_global_config telemetry:false; verify with get_health. See docs/compliance/PRIVACY.md for the full disclosure.

Skills

FeatureBoard ships a Claude Skill in skills/ for the churn workflow this README describes:

  • skills/featureboarding.skill — boards substantive dev requests automatically (no need to say "put it on the board") and churns the queue with parallel sub-agents per ticket dispatch blocks.

To install: drag the .skill file into Claude -> Settings -> Capabilities, or just open the file.

Data & storage

  • Boards are plain markdown; a .featureboard/index.json sidecar caches the ticket counter. Markdown is always authoritative.

  • Ticket ids are inferred from existing tickets in each file, so a board keeps its prefix regardless of folder name.

  • Writes are atomic (temp-file + rename).

Build & develop

Requires Node 18+.

npm install                       # MCP SDK + zod
npm run check                     # syntax-check every server module
node --test                       # unit tests (1232)
npm run smoke                     # end-to-end stdio smoke test (no Claude Desktop needed)
npm run build && npm run bundle   # preflight, then pack featureboard-<version>.mcpb

Run the server directly over stdio:

FEATUREBOARD_DATA_DIR=/path/to/boards npm start

Nightly tests

npm run nightly runs the suite headlessly per nightly_tests.json and records a timestamped result under .featureboard/nightly/ (kept to keepRuns). The exit code mirrors the run so a scheduler can alert on regressions; if testLogPath points at a board's test_runs.md, the result is appended there so get_test_runs and the board's 🧪 Tests panel surface nightly runs next to manual ones. MCP servers have no daemon, so scheduling lives outside the server — point cron or Windows Task Scheduler at the script.

Troubleshooting

bash fails, the sandbox won't start, or a scheduled task silently stopped? That's almost always the Claude Desktop Cowork sandbox filling its disk — not a FeatureBoard bug — and it surfaces as useradd failed: exit status 12: cannot create directory /sessions/…, Workspace unavailable, or checks that never return. The fix is to reset the sandbox's disk image from your computer (your boards and repos are never touched). Full symptoms, the root cause, and step-by-step macOS/Windows reset instructions are in docs/TROUBLESHOOTING.md.

License

MIT © Lewis Valentine

Available Tools

217 tools
activate_licenseActivate license keyA
Idempotent

Activate a commercial license. Two modes — provide exactly one: (1) key, a signed license key string pasted from the licensor; or (2) email + orderId from your purchase receipt, in which case the server fetches the signed key for you from the featureboard.ai claim API (a single outbound HTTPS POST carrying just that email + order id) and then verifies it exactly the same way as a pasted key. Either way, verification itself is fully offline. Unblocks writes for commercial use.

Inputs: key, email, orderId.

add_attachmentAdd attachmentA
Idempotent

Attach a file path or URL to a ticket (stored as [Attachments: ...] on the ticket line). Idempotent: attaching the same item twice is a no-op.

Inputs: ticket (required), project (required), attachment (required).

add_companyAdd a CRM companyC

Create a company in the project's CRM (crm/companies/.json). Slug is derived from the name and de-duplicated. Returns the new company record.

Inputs: name (required), project (required), notes, domain.

add_company_agreementAdd a company contract/licenseA

Record a contract or license on a CRM company (stored on the company, alongside contacts). kind 'contract' or 'license'; optional template (from generate_contract), title, value, seats, term, expiresAt, status, notes. Returns the new agreement.

Inputs: kind (required), company (required), project (required), term, +7 more.

add_contactAdd a CRM contactB

Add a contact (name, email, role, phone) to a company. Contact ids are unique within the company.

Inputs: name (required), company (required), project (required), role, +2 more.

add_crm_messageAdd a CRM inbox messageA

Add an incoming message to the CRM inbox (starts pending review). Useful for logging inbound emails/leads that need triage and approval.

Inputs: project (required), body, from, name, +4 more.

add_decisionAdd an architecture decision recordA

Append a new ADR to a project's decision log (decisions.md): context, decision, consequences, and any tickets it relates to. Auto-numbers ADR-. Append-only — never rewrites prior ADRs. Relevant ADRs surface automatically in ticket work packets.

Inputs: title (required), project (required), decision (required), context, +2 more.

add_featureAdd featureB

Add a feature to a board's featurelist.md. Returns the new ticket (FBF-###).

Inputs: title (required), project (required), ref, labels, +8 more.

add_features_bulkAdd features (bulk / brainstorm)A

Add several features at once. Use this after brainstorming: you generate the ideas, this persists them. Returns the created tickets.

Inputs: project (required), features (required).

add_kb_docAdd/update a kb docA
Idempotent

Write a markdown doc into a board's kb/ folder (a per-project knowledge base beyond the scratchpad): title + markdown body, stored as kb/.md. Calling again with the SAME title updates that doc in place; a different title that slugifies to the same filename gets a numeric suffix instead of clobbering the original. Docs are keyword-matched into work packets automatically via get_work_packet.

Inputs: title (required), content (required), project (required).

add_leadAdd a leadA

Add a sales lead to the project's leads store (crm/leads.json). Status defaults to 'new' (pipeline: new → contacted → qualified → won/lost). Optional value and lat/lng power the pipeline value and the leads map.

Inputs: name (required), project (required), lat, lng, +6 more.

add_lead_areaAdd a lead areaA

Define a circular geographic area (name + centre lat/lng + radius km) for the leads map. leads_map then tags each mapped lead with the areas it falls in and rolls up lead counts + pipeline value per area.

Inputs: lat (required), lng (required), name (required), project (required), +1 more.

add_lead_interactionLog a lead interactionA

Append a touchpoint to a lead's interaction log: kind (call/email/meeting/note/visit/other) + a note, timestamped. Builds the per-lead history.

Inputs: id (required), note (required), project (required), at, +1 more.

add_media_commentComment on a media assetA

Add a threaded comment to a gallery asset (a discussion thread, distinct from pin annotations). Pass parentId (a comment id from get_media / list_media_comments) to reply to an existing comment. Returns the new comment and total count.

Inputs: body (required), name (required), project (required), author, +1 more.

add_pageAdd/update a website pageA

Add or update a sub-page of the project site (rendered to site/.html), with its own title and sections. The home page stays managed by set_site. Re-renders all pages so theme/gate stay consistent.

Inputs: slug (required), project (required), seo, title, +1 more.

add_productAdd productB
Idempotent

Add a product to a board's product list (used for tagging tickets via [Product: …]).

Inputs: name (required), project (required).

add_review_commentAdd review commentA

Attach a PR-style review comment to a ticket (optionally anchored to a file and line). Unresolved review comments surface in the ticket's next work packet (get_work_packet.reviewComments) so the next agent acts on the feedback, and — when the ticket is in Review — a comment sends it back into next_task's queue. Also recorded on the ticket's audit history.

Inputs: ticket (required), comment (required), project (required), file, +2 more.

add_sourceAdd/update a research sourceA
Idempotent

Save a research source (paper, article, reference) into a board's sources/ library — one file per source, separate from the synthesized kb/ notes, stored under a citation header (title, source/author, url, ticket, tags) and indexed into the RAG (source/). THREE ways to supply the text, in priority order: (1) path= a local file — .pdf (optional pdf-parse dep), .html, or any text/markdown is read + extracted automatically; (2) url= a web page or PDF — fetched and extracted automatically (title/source auto-filled); (3) text= the raw text directly. With url/path, title/source are auto-detected (override by passing them). If a PDF is scanned or a page is JS-rendered, the tool returns { needsText: true, reason } — read it yourself and call again with text=. Calling again with the SAME title updates in place. Use this for the sources; use add_kb_doc / append_research for YOUR notes about them.

Inputs: project (required), url, path, tags, +4 more.

annotate_mediaAnnotate a media assetA

Add a pin-based comment/annotation to an asset. Optional x/y locate the pin (e.g. 0-1 relative coordinates on an image or report). Returns the new annotation (with a stable id) and the total count.

Inputs: name (required), text (required), project (required), x, +2 more.

append_researchAppend a research findingA

Capture ONE research finding into a ticket's durable research doc AS YOU GO (FBMCPF-333). Appends to the same kb doc get_work_packet auto-attaches downstream (research-), creating it on the first call and appending on later ones — so findings accrue in the always-indexed kb/ knowledge base instead of the ephemeral scratchpad. Prefer this over append_scratchpad for anything worth remembering across tickets: call it repeatedly during research rather than saving one brief only at the end.

Inputs: ticket (required), finding (required), project (required).

append_scratchpadAppend to scratchpadA

Append a line or block to a board's scratchpad.md, preserving existing notes. Mention a ticket id (e.g. FBF-12) to have it surface in that ticket's work packet.

Inputs: text (required), project (required).

apply_site_templateStart the site from a templateA
Destructive

Seed the project website from a starter template (landing, docs, blog): sets title/tagline/theme/sections and any starter pages, then renders. Replaces the current site config — use set_site/add_page to refine after.

Inputs: project (required), template (required), title.

assign_sprintAssign sprintA
Idempotent

Move one or more tickets into a sprint — sets the sprint: label, replacing any existing sprint label. Pass sprint: null to send tickets back to the backlog.

Inputs: sprint (required), project (required), tickets (required).

auto_configure_analyticsAuto-configure external analyticsA
Idempotent

Derive the external analytics read config from the site's existing tracking settings (set_site_analytics), so you don't retype the domain/property, and enable the proxy. Errors if the site has no analytics configured yet.

Inputs: project (required).

book_meetingBook a call/demo with a CRM contactA

Schedule a call, demo, or meeting with a CRM company (and optionally a specific contact within it). Validates the company exists (list_companies) and the contact belongs to it. Time is an ISO timestamp; stored under crm/bookings.json with status 'scheduled'.

Inputs: at (required), company (required), project (required), type, +4 more.

bug_impact_scanBug impact scanA
Read-only

Given a bug (by ticket, or an ad-hoc title/description), rank the existing features most likely affected, by keyword overlap and shared product. Use it when logging a bug to spot regressions and linkage candidates.

Inputs: project (required), title, ticket, description.

cancel_bookingCancel a bookingA
Idempotent

Cancel a scheduled booking by id (from list_bookings), optionally with a reason. Idempotent: cancelling an already-cancelled booking is a no-op.

Inputs: id (required), project (required), reason.

capture_askCapture an external request as a ticketA

Structure ONE pasted external request — a Slack message, forwarded email body, chat snippet — into a feature or bug via the same heuristics as validate_feedback (type/product/priority keywords, model/cap intake guard), labeled ask: with the requester recorded in the description. This is paste-to-structure, not a live intake listener.

Inputs: text (required), project (required), from, source.

check_acceptanceCheck an acceptance criterionA
Idempotent

Toggle the checkbox on acceptance criterion #index (1-based) of a ticket's requirements pad. Hand-added sections are preserved. done defaults to true.

Inputs: index (required), ticket (required), project (required), done.

check_updatesCheck for FeatureBoard updatesA
Read-only

Explicitly check featureboard.ai for a newer FeatureBoard release. This makes exactly ONE outbound HTTPS GET request — to https://featureboard.ai/downloads/latest.json — and ONLY when you call this tool; it never runs automatically (no polling, no startup check, no background timer). It is a plain GET with no request body: nothing about you, your board, or this machine is sent. Compares the manifest's version against THIS running server's own version (read from its own package.json) and reports whether an update is available, plus both download links — featureboard.plugin for Claude/Cowork installs, featureboard-mcp.zip for Cursor/Grok Build/other MCP clients. Fails soft on any network problem (timeout, offline, bad response) — never throws; call it again later if it couldn't reach the server.

Inputs: no named parameters.

churn_reconcileReconcile logged vs git churnA
Read-only

For Done tickets with tagged commits, compare the additions/deletions logged in the work log against the git-actual numstat of their commits. Git-actual comes from recorded commit events (FBMCPF-188) or, failing that, a live git log --grep + numstat cached by hash. Reports per-ticket loggedAdd/loggedDel vs gitAdd/gitDel with a drift ratio (worst first), plus an overall churnAccuracy also surfaced on get_health. Paginated (FBMCPB-42): returns the worst-drift page by default (limit/offset, mirroring list_tasks) so a big board stays inside the token budget — the totals/churnAccuracy rollup is always over ALL reconciled tickets. Pass driftThreshold to omit tickets whose drift ratio is below it, or full:true for every row.

Inputs: project (required), full, limit, offset, +1 more.

cleanup_worktreeRemove a ticket's git worktreeA
DestructiveIdempotent

Remove a ticket's git worktree once its branch has been merged back (git worktree remove + prune). REFUSES when the worktree has uncommitted changes unless force:true. No-ops with a message when no worktree is registered for the ticket, and never force-deletes a path git doesn't recognise as a worktree. Leaves the ticket/ branch intact (merge it back first with the merge-back guidance).

Inputs: ticket (required), project (required), force.

close_sprintClose sprint & generate reportsA
Idempotent

Close a sprint and generate four audience-specific close-out reports (marketing, sales, technical, executive) from its tickets, work log, and metrics (velocity, tokens, $ cost, ADRs touched, CRM ticket links). Refuses to close while the sprint still has open (non-Done) tickets unless force:true. Writes reports//.md pads under the project and returns their paths, a metric summary, and a per-audience LLM prompt (packet + brief) for richer draft copy. Posts a Slack summary when the project has Slack configured (never fails the close on a Slack error). Also handles the sprint's remaining open tickets per rolloverMode (FBMCPF-197): 'review' (default) returns a categorized rollover plan without moving anything; 'auto' retags P0/P1 tickets into nextSprint (or flags them rollover-pending if no nextSprint given), labels P2/P3 tickets rollover-candidate for human review, and drops the sprint label from P4+/unprioritized tickets back to the backlog; 'off' skips rollover handling entirely. The result's existing shape is unchanged — rollover info is added as a rollover section.

Inputs: sprint (required), project (required), force, nextSprint, +1 more.

code_file_mapMap the codebaseA
Read-only

Recursively map the project's codeLocation: total file count + bytes, counts by extension, and the files that exceed the split thresholds (lines/bytes) as split candidates (worst first) — useful for spotting oversized modules to decompose. With symbols:true, also returns a per-file list of top-level exported functions/classes/consts for JS/TS files (regex-based, capped per file) — a lightweight symbol map for navigation.

Inputs: project (required), symbols, splitBytes, splitLines.

commit_featureCommit a finished featureA

If git integration is enabled for the project, commit (and optionally push) the current changes in the project's code repo with a message like 'FBMCPF-##: title' — mirroring the original OpenClaw git flow. For graduated projects, also refreshes a read-only snapshot of the pad (featurelist.md, buglist.md, scratchpad.md, agent_work_log.md, config) into /.featureboard/ and includes it in the same commit — the central pad stays authoritative, this is a one-way mirror. No-ops with a reason when disabled. When push is omitted, the effective push behavior is resolved from gitMode (project override via set_git_config, else the account-wide default via set_global_config, else "commit-only") — "ask" commits without pushing and returns a note asking you to confirm before pushing again with push:true; it never pushes silently. Passing push explicitly always overrides gitMode. When the autoStatusOnCommit config key is on, closing keywords in the commit message ('closes/fixes/resolves FBB-12') move that ticket to Done (or Review if requireReview is on) — same-project tickets only (FBMCPF-200). Runs on this machine using its git credentials. Without an explicit paths param, staging is 'git add .' — ALL pending changes in the tree land in this ticket's commit, so pass paths when other tickets' edits may be pending.

Inputs: project (required), push, paths, title, +2 more.

company_priority_ticketsA company's tickets by priorityA
Read-only

List a company's linked board tickets, split into features and bugs and ranked by priority (highest first, i.e. lowest number). Uses the ticket↔customer links; reports any linked ids no longer on the board as missing.

Inputs: company (required), project (required).

convert_leadConvert a lead to a companyA

Convert a qualified lead into a CRM company, carrying over its fields (name, website→domain, a notes summary) and optionally seeding a contact from the lead's person/email/phone. Marks the lead won and records the company it became. Errors if already converted.

Inputs: id (required), project (required), companyName, createContact.

coverage_by_productTest coverage by productA
Read-only

Roll up, per product, how many of its tickets have at least one recorded test run vs none, so testing gaps are visible on the board. Includes an overall rollup and the untested tickets per product.

Inputs: project (required).

create_campaignCreate a marketing campaignA

Create a marketing campaign with a recipient list and a send batch size. Recipients are validated + de-duplicated; sending is left to the user/a connector (this tracks the campaign and computes send batches). Returns the campaign + stats. When the project config voiceLint is on, the body copy is scored for AI-writing tells and the result is attached as voice (warn-only, never blocks the draft).

Inputs: name (required), project (required), recipients (required), body, +2 more.

create_projectCreate projectA

Create a new board folder with empty featurelist.md and buglist.md. Returns the derived ticket prefix.

Inputs: name (required), description.

create_sprintCreate sprintA
Idempotent

Create (or update) a named sprint on a board, with optional start/end dates and a one-line goal. The registry is persisted in the project config; tickets join a sprint via a sprint: label (see assign_sprint), so label-only sprints written by the board UI keep working.

Inputs: name (required), project (required), end, goal, +2 more.

create_worktreeCreate a git worktree for a ticketA
Idempotent

Create (or reuse) an isolated git worktree for a ticket so several tickets can be worked in PARALLEL - each sub-agent edits its own checked-out directory on branch ticket/, sharing one .git object store, never the shared repo working tree. Created at /. IMPORTANT SYNC CAVEAT: worktrees are placed OUTSIDE the code repo by default (sibling directory -worktrees/), configurable via the project config key worktreeDir - under Cowork, a worktree created INSIDE a synced repo mount can corrupt git internals or fail to sync, so this tool REFUSES a worktreeDir inside the repo and never auto-creates worktrees in the repo itself. Reuses an existing worktree at the path; creates branch ticket/ off baseRef (or current HEAD) when absent. Returns the worktree path, branch, and merge-back guidance. Errors clearly when the project has no codeLocation, the path is not a git repo, git is too old (< 2.5), or a non-worktree directory squats the path.

Inputs: ticket (required), project (required), baseRef.

customer_portalCustomer portalA

Build a per-customer portal page for a CRM company: their contacts plus the board tickets linked to them (link tickets with link_customer_ticket). Returns self-contained HTML; with save:true it also writes the page into the media gallery as portal-.html and returns its path.

Inputs: company (required), project (required), save.

daily_planDaily planA
Idempotent

Plan TODAY: pick the day's slice of the priority queue (default budget 5M logged tokens ≈ one day of a 25M week), assign each ticket a model from the roster (fable=orchestration/design, opus=architecture/invariants, sonnet=standard implementation, haiku=mechanical docs/copy) and an effort level (low/medium/high). apply:true writes model:/effort: labels onto the tickets. Returns dispatch groups: haiku/sonnet/opus tickets safe to run as parallel sub-agents, fable inline in the orchestrator (see server/routing.js). Pair with the daily_plan prompt to execute.

Inputs: project (required), apply, sprint, budgetTokens.

decompose_featureDecompose featureA
Destructive

Replace one feature with a set of linked subtasks. You provide the subtasks; this creates them (each linked to the parent) and deletes the parent. Returns the new tickets.

Inputs: ticket (required), project (required), subtasks (required), keepParent.

delete_taskDelete taskB
Destructive

Permanently remove a task from its board.

Inputs: ticket (required), project (required).

deploy_siteDeploy the websiteA

Re-render the project's site and publish it by committing (and optionally pushing) it through the git integration — the MCP equivalent of the old website deploy. The site lives at /site/ by default, or at the project's websiteLocation when set (a shipped site outside the pad, in its own repo — see set_project_config). When websiteLocation / gitTargets.websiteRepo is configured the commit runs in that website repo; otherwise it runs where the pad site lives. Requires git integration enabled (set_git_config); no-ops with a reason otherwise. When push is omitted, the effective push behavior is resolved from gitMode the same way as commit_feature (project override, else account-wide default, else "commit-only"); "ask" never pushes silently. Runs on this machine using its git credentials.

Inputs: project (required), push, message.

disable_login_gateDisable the site login gateC
Idempotent

Turn off the project site's passcode gate and re-render the page without it.

Inputs: project (required).

dismiss_cleanup_findingDismiss a cleanup findingA
Idempotent

Suppress a scan_board_cleanup finding from future scans WITHOUT deleting anything — for false positives or findings you've consciously accepted. Pass the finding's stable id (shown on each duplicate/stale/unlabeled/SLA finding) and an optional reason. Dismissals are append-only; future scans hide the finding and report dismissedCount. The id is a hash of the finding's type+ticket, so it keeps matching across rescans until that ticket changes category.

Inputs: project (required), findingId (required), reason.

draft_emailDraft an emailA

Compose and save an email draft in the project mail center (does not send — there is no mail connector; the user or a future connector sends). Recipients are validated. Optionally tie it to a CRM company. When the project config voiceLint is on, the body text is scored for AI-writing tells and the result is attached as voice (warn-only, never blocks the draft).

Inputs: to (required), project (required), cc, body, +2 more.

draft_shareDraft a social shareA

Save a reviewable social-share draft for a gallery item — you write the copy, this persists it (never posts). Platform 'x' (≤280 chars) or 'linkedin' (longer); over-limit copy is rejected. There is no live-publish connector: drafts are for the user to review and post. Use list_shares to review. When the project config voiceLint is on, the draft text is scored for AI-writing tells and the result is attached as voice (warn-only, never blocks the draft).

Inputs: text (required), project (required), platform (required), asset.

drift_recordRecord a drift scoreA

Record a 0–100 fidelity score for one ticket in a drift run (verdict is derived: >=80 aligned, 50–79 partial, <50 drift — or pass your own). Provide a short gap explaining any shortfall, and optionally the files you checked. Upserts by ticket.

Inputs: score (required), ticket (required), project (required), gap, +3 more.

drift_remediateApply drift remediationA
Destructive

One-click remediation across a run's flagged tickets: action 'file_bugs' files a linked, drift-labeled bug per gap; 'reopen' moves them back to Todo; 'relabel' adds a 'drift' label. verdicts selects the bands to act on (default ['drift']). Pass dryRun:true to preview. Records what it did on the run.

Inputs: action (required), project (required), runId, dryRun, +1 more.

drift_reportDrift evaluation reportA
Read-only

Aggregate a drift run: per-ticket scores, mean fidelity, verdict counts, drift rate, and — for sampling — a 95% Wilson confidence interval on the true drift fraction extrapolated to the whole Done population. Lists the flagged (partial/drift) tickets worst-first with their gaps, and any pending (unscored) tickets.

Inputs: project (required), runId.

drift_startStart a drift evaluationA

Begin a drift-evaluation run over a board's Done tickets. mode 'sample' evaluates a seeded random subset (fast statistical estimate); mode 'full' evaluates every Done ticket. Returns a runId + the tickets to score. Then, for each ticket, compare its scope/description/DoD + work log against the actual code it touched (use get_work_packet and the project's codeLocation) and call drift_record with a 0–100 fidelity score; finish with drift_report. Use the evaluate_drift prompt to run the whole loop.

Inputs: project (required), mode, seed, type, +1 more.

edit_mediaEdit a text media assetA

Directly edit an existing text/report asset (find/replace, append, or prepend) and save the result as a new version — the prior copy is archived (edit-media). For images, use refine_media or image generation instead.

Inputs: name (required), project (required), find, append, +2 more.

edit_site_sectionEdit a website sectionA

Live editor: patch one website section by index (heading and/or body), or append a new section when index is omitted. Re-renders the page.

Inputs: project (required), body, index, heading.

enable_login_gateEnable the site login gateA
Idempotent

Turn on an optional passcode gate for the project's hosted site. NOTE: this is a soft client-side gate (the passcode ships in the page) — casual gating, NOT real authentication; real auth needs a hosting layer. Requires a passcode.

Inputs: project (required), passcode (required), message.

enrich_leadEnrich a leadA
Idempotent

Record website-sourced details on a lead (only provided fields are set): website, domain, phone, industry, description, contactName, employees, email, city, source, value. Use the pull_lead_website prompt to fetch + extract these from the lead's site first, then persist them here.

Inputs: id (required), project (required), city, email, +9 more.

estimate_workEstimate workA
Read-only

Per-ticket token estimates for all open tickets, derived from the board's own history: a cap: label wins, then the median actual spend of Done tickets in the same product, then the board median, then a documented default. Each estimate carries its basis, confidence, spend so far, and a suggested model (model: label or heuristic).

Inputs: project (required).

eval_model_matrixEval: model up/downgrade effectiveness at test timeA

FBMCPF-148 — run a ticket's per-model test variants (test/..test.js, from generate_multi_model_tests / save_generated_test) against seeded regressions to see which tier's tests actually catch bugs. Seeds deterministic textual mutations (a built-in set, or caller-supplied find/replace patch specs) into a COPY of targetFile inside a fresh temp dir — the repo is never touched — runs each model's variant file with node --test before and after, and reports per-model defects caught, unique-catch rate (defects only that tier's tests caught), an overlap matrix, and cost per caught defect (tokensByModel × pricing.js rates). Omit targetFile to just run the baseline pass/fail matrix (no seeded mutations). Writes nothing to the repo unless writeEvidence:true, which appends the formatted readout to docs/EVIDENCE.md under codeLocation — mode is required so a demo run can never be silently mistaken for real defect data.

Inputs: mode (required), ticket (required), project (required), mutations, +3 more.

eval_reportEval reportA
Read-only

Compare board-workflow vs chat-workflow trials using label conventions: experiment:board / experiment:chat marks a ticket's arm, and an optional pair: label ties a board trial to its chat counterpart. Returns every labeled trial (tokens and $ cost from the work log, additions/deletions, wall-clock days, rework = linked bugs within 7 days of completion), per-arm medians/totals (including totalCost), matched pairs with a token ratio, and a one-line summary.

Inputs: project (required).

export_auditExport compliance & traceability reportA
Read-only

Unified compliance/traceability export: for one ticket or the whole board, merges the existing audit primitives into a single report — field-change events (status/priority/label moves), work-log sessions, sub-agent dispatch records, requirements pads with acceptance-criteria state, review comments with resolution, decision-log entries, correlated commits (recorded-first with git log --grep fallback), and drift-harness scores. Includes a board-level compliance summary: status counts, acceptance coverage, unresolved reviews, work totals, drift flags, and Done tickets with no correlated commit. Formats: json (structured), markdown (human-readable dossier), csv (flat chronological trail rows for BI). Read-only.

Inputs: project (required), format, ticket, maxCommits, +1 more.

export_metricsExport metrics / work logA
Read-only

Flat-file export of analytics for external BI/spreadsheet use, mirroring export_tasks: what:'worklog' exports the per-event work log (date, ticket, model, tokens, additions/deletions); what:'completions' exports status counts + completions-by-date. Formats: json or csv. Read-only.

Inputs: project (required), what, format.

export_tasksExport tasksA
Read-only

Export a board's tasks to json, csv, or markdown for use outside FeatureBoard (e.g. sharing with a PM tool). Round-trips through import_tasks. Read-only.

Inputs: project (required), format.

generate_contractGenerate a contractB

Fill a standard contract template with the given fields and return the draft markdown. Optionally auto-fills customer_name from a CRM company, and with save:true writes the draft into the media gallery. Drafts are stamped to review with counsel — not legal advice.

Inputs: project (required), template (required), save, vars, +1 more.

generate_multi_model_testsGenerate multi-model test variantsA
Read-only

For a bug/ticket, fan one generation prompt out across model tiers (default fable, opus, sonnet) — each surfaces different failure concepts. Returns the SAME prompt once per tier plus a per-tier storage path (test/..test.js) and instruction. Read-only: run each tier yourself, then submit results to save_generated_test. Builds on suggest_test_stub / generate_test (FBMCPF-102).

Inputs: ticket (required), project (required), models, module, +1 more.

generate_testGenerate a test from a promptA
Read-only

Generate a FULL node:test file (path + content) from a prompt and/or a ticket — one test() block per described behaviour, not just the single boilerplate stub. Optionally imports a target module. Read-only: returns the file for you to write under test/.

Inputs: project (required), module, prompt, ticket.

get_agent_monitorAgent monitor v2 (live sessions, stalls, spend)A
Read-only

Live snapshot of the board's currently-running work: every In Progress ticket with elapsed time since it went In Progress (from the ticket_events.jsonl audit log, falling back to its earliest work-log entry or createdDate when there's no recorded status event), its last event (most recent audit event or work-log entry, whichever is newer) with age, token spend so far vs its cap: label and the resulting spend ratio, and a stalled flag (no event/work-log activity within stallMinutes, default 30). Also reports costSoFar and capCost in dollars (via project-config-overridable pricing; capCost is null when no model can be inferred for the ticket). Each ticket also carries lastDispatch ({worker, model, parallel, note, ageMinutes}, null if record_dispatch was never called for it) — who's actively working it, a sub-agent or the orchestrator — so the board can render an orchestration chip without a separate call. Sorted most-recently-active first, with a top-level summary (count, stalledCount, subAgentCount, parallelCount, totalSpend, totalCap, totalCostSoFar, totalCapCost, stalledTickets). Pairs with churn mode: a stalled ticket mid-churn usually means the agent is stuck or has gone quiet. Use it to see what's underway, who/what is running it, and catch stuck tickets.

Inputs: project (required), asOf, stallHours, stallMinutes.

get_boardOpen the board (UI)A
Read-only

Return the FeatureBoard board UI as a self-contained HTML document, ready to render as a Cowork artifact. This is THE way to satisfy any natural-language request to see the board — "open/show the board", "show the featureboard", "what's on my plate", "how are we looking", "give me a status", "show velocity/analytics". Do NOT hand-write your own board: take the returned html, write it to a file, and pass it to create_artifact (use artifact id "featureboard-board"; if a board artifact is already open, reuse it via update_artifact instead of creating a duplicate). Use the mcp_tools array in this response VERBATIM as the artifact's mcp_tools (do not hand-pick tools from memory — the board's buttons and analytics dashboard call back into exactly these tools, and any you omit will fail with "not in this artifact's mcp_tools allowlist").

Inputs: no named parameters.

get_brandingGet project brandingA
Read-only

Return the project's brand kit — name, tagline, words, voice, colors, logo, font — plus a ready-to-inject generation instruction, a CSS :root cssVars snippet for web, and which fields are still missing. Call this before generating any branded asset to stay consistent.

Inputs: project (required).

get_campaignGet a campaignB
Read-only

Full campaign incl. recipients, open stats, and the send-batch sizes.

Inputs: id (required), project (required).

get_check_resultsGet background check resultsA
Read-only

Collect the results of a background static-check run: by runId, else the newest run for a ticket, else the newest run overall. Returns the run's status (running | passed | failed | error), per-check results (name, status, captured output) and ageSeconds. This closes the async loop: commit_feature starts checks in the background so the orchestrator can commit and immediately keep working; between tickets (and before ending the session) collect any uncollected runs here — a failed run means fix it now or file a bug before closing out. Read-only, zero tokens. The first time a FAILED run is collected for a ticket it's recorded as a 'checks' audit event on that ticket.

Inputs: project (required), runId, ticket.

get_companyGet a CRM companyA
Read-only

Full company record including its contacts. Throws if the company id isn't found.

Inputs: id (required), project (required).

get_emailGet an emailA
Read-only

Full email message by id (from list_mail).

Inputs: id (required), project (required).

get_git_configGet git integration configA
Read-only

Read the project's optional git integration settings (enabled, remote, branch, push, messagePrefix, gitMode). Also reports the RESOLVED push mode (resolvedGitMode) and where it came from (gitModeSource: "project" | "global" | "default") — the project's own gitMode wins, then the account-wide default (set_global_config), then "commit-only" (never push). Disabled by default.

Inputs: project (required).

get_global_configGet account-wide configA
Read-only

Read FeatureBoard's account-wide settings that apply across every project unless a project overrides them via set_git_config. gitMode (default "commit-only") plus, when captured, planLimits — the two weekly Claude-Max usage meters ({fablePct, allModelsPct, capturedAt, resetAt, targetRatio}) that drive blend tracking on get_health/get_metrics/plan_budget (FBMCPF-278/279). Stored at /.featureboard.global.json.

Inputs: no named parameters.

get_healthGet project healthA
Read-only

Composite 0-100 health score with grade and breakdown: bug pressure, feature progress, momentum (recent tokens), and freshness (staleness of open work).

Inputs: project (required).

get_kb_docGet a kb docA
Read-only

Read one kb doc's full markdown content by slug (or title — it gets slugified). Returns null-ish (not found) when no such doc exists.

Inputs: slug (required), project (required).

get_live_activityGet live activity (sub-agent visibility)A
Read-only

Read-only git/filesystem ground truth about what coding sub-agents are doing RIGHT NOW, for one project or (omit project) a rollup across every project with a codeLocation configured. Sub-agents deliberately never write the board mid-flight (only the orchestrator sets status/logs work/commits), so between a ticket going In Progress and coming back Done, the board itself has nothing new to say — the filesystem is the only truth. Per repo (code + website, when configured): dirty files (capped list + total count) and pending additions/deletions, commits in the last sinceMinutes, and OTHER git worktrees (a live sub-agent edit surface) with their branch + dirty-file count. Also surfaces each repo's (and each worktree's) .fb-progress file — the sanctioned sub-agent progress channel: tell sub-agents in their brief to append one-line timestamped notes there at each major step (created → tests written → suite green, etc.) — plus recently-modified files and the cheap board-side signals (In Progress count, last work-log age). Use this for stalled-ticket triage (get_agent_monitor flags a stall from board events; this answers 'but is anything actually moving?') and for a cross-project 'what's live right now' rollup on Mission Control. In all-projects mode, quiet projects (nothing within sinceMinutes) are returned as plain name strings instead of full objects, appended after the active ones.

Inputs: project, maxFiles, maxCommits, sinceMinutes.

get_mediaView a media assetA
Read-only

View one media asset: its metadata, size, and (by default) content — UTF-8 for text/report assets, base64 for images — plus its revision history (prior versions with the prompts used). Pass a version id to view an archived revision instead of the current one; set withContent:false for metadata + history only.

Inputs: name (required), project (required), version, withContent.

get_metricsGet metricsC
Read-only

Read-only snapshot: feature/bug counts by status, completions by date, and velocity from the work log (tokens, additions/deletions, active days, recent tokens, and $ cost by model — see project config "pricing" to override the default Anthropic API rates).

Inputs: project (required).

get_project_configGet project configA
Read-only

Read a board's settings: products, code location, agent model, prefixes, website, description, pricing overrides. Merges MCP-managed config over the legacy project_config.json.

Inputs: project (required).

get_rag_explorerOpen the research RAG explorer (UI)A
Read-only

Return the Research RAG Explorer UI as a self-contained HTML document, ready to render as a Cowork artifact — the visual front door to the local research RAG (FBMCPF-263/264). It lets the user browse a board's kb/ docs (including per-ticket research briefs), add new docs (add_kb_doc), and query the BM25 index (rag_search over kb + repo docs/ + Done-ticket summaries, with a search_kb fallback). Use this for natural-language asks like "show/open the RAG", "what's in the knowledge base", "let me query the research index". Do NOT hand-write your own explorer: take the returned html, write it to a file, and pass it to create_artifact (use artifact id "featureboard-rag-explorer"; if one is already open, reuse it via update_artifact). Use the mcp_tools array in this response VERBATIM as the artifact's mcp_tools — any tool you omit fails with "not in this artifact's mcp_tools allowlist".

Inputs: no named parameters.

get_regressionsGet regressionsA
Read-only

Regression view: bugs grouped under the feature they're linked to (sorted by open-bug count), plus unlinked bugs. Surfaces which shipped features are at risk. Link bugs to features (link_tasks) to populate it.

Inputs: project (required).

get_requirementsGet ticket requirementsA
Read-only

Read a ticket's requirements pad as structured intent / assumptions / acceptance criteria (with done flags) / open questions, plus the raw markdown. Returns null when no pad exists.

Inputs: ticket (required), project (required).

get_scratchpadGet scratchpadA
Read-only

Read a board's freeform scratchpad.md - a per-project notes surface for context, decisions, and reminders that Claude and the board share. Returns the raw markdown.

Inputs: project (required).

get_siteGet the project websiteC
Read-only

Read the project's splash/website config (title, tagline, theme, sections, login gate). Returns defaults if none built yet. FBMCPB-64: when the resolved site directory (websiteLocation, else /site/) holds an index.html FeatureBoard did not generate, the response carries an unmanaged block — the config is only the site.json sidecar, so treat empty tagline/0 sections as "no sidecar", not "no website".

Inputs: project (required).

get_site_trafficGet site traffic (analytics proxy)A
Read-only

Read proxy for site traffic: fetch the configured provider's stats (Plausible/umami) using the FEATUREBOARD_ANALYTICS_KEY env var and return normalised numbers so the board can show traffic. Degrades gracefully — when disabled, unconfigured, or missing a key it returns the exact request URL so you can fetch it yourself.

Inputs: project (required), period, metrics.

get_sourceGet a research sourceA
Read-only

Read one source's full raw text + citation fields by slug (or title — it gets slugified). Returns null-ish (not found) when no such source exists.

Inputs: slug (required), project (required).

get_sprint_reportRead sprint reportsA
Read-only

Read the close-out reports written by close_sprint. With no sprint: list sprints that have reports. With a sprint but no audience: the manifest + which audiences exist. With sprint + audience (marketing|sales|technical|executive): that report's markdown.

Inputs: project (required), sprint, audience.

get_steering_statusSteering status (observability, no pass)A
Read-only

FBMCPF-319: read-only observability into the steering loop for a project — WITHOUT running or mutating a pass (unlike steer_project). Returns the persisted steering.json state (lastSteeringAt, everSteered, how many Done tickets have been claimed/reviewed + the recent reviewed ids, and goalOnlyStreak — the consecutive goal-only passes that gate the auto-stop) plus a live snapshot: goal/goalMissing, open-ticket count, how many Done tickets are still unreviewed, and the tickets filed since the last steering pass (a proxy for what the last pass produced). Use it to answer 'where is steering at?' without kicking off a new wave.

Inputs: project (required).

get_taskGet taskA
Read-only

Get the full details of a single task by its ticket ID (e.g. FBF-12).

Inputs: ticket (required), project (required).

get_test_pageGet a test pageA
Read-only

Read one test page's HTML by name.

Inputs: name (required), project (required).

get_test_runsGet test runsA
Read-only

Read recorded test runs (most-recent first) plus a summary: total runs, latest result, and whether the latest is passing.

Inputs: project (required), limit.

get_ticket_diffGet ticket diffA
Read-only

Capture the code changes made for a ticket: find commits in the project's code repo (codeLocation / gitTargets.codeRepo) whose message mentions the ticket id and return, per commit, a summary (hash/author/date/subject) plus a size-capped unified diff (git show). Read-only — never writes or fetches. context sets the unified context-line count; maxBytes caps the total diff bytes returned (over-cap diffs are truncated with a notice, later commits omitted). Returns a warning (not an error) when the project has no codeLocation, the path is not a git repo, or no commits mention the ticket. Pass semantic:true to also get a deterministic semantic view (no LLM): formatting-only hunks stripped, files ordered core → tests → docs/config, mechanical renames flagged, plus a ready-to-use review-summary prompt — assistive, verify against the raw diff.

Inputs: ticket (required), project (required), context, maxBytes, +2 more.

get_ticket_historyGet ticket historyA
Read-only

Full audit timeline for one ticket: recorded field-change events (status moves, priority moves, label/sprint changes, due-date edits — captured automatically by set_status/update_task/assign_sprint) merged in chronological order with that ticket's work-log entries (tokens/additions/deletions per work session). Tolerates tickets with no recorded events yet (pre-FBMCPF-142 tickets still show their work-log history).

Inputs: ticket (required), project (required).

get_timeline_dataGet timeline data (piano-roll)A
Read-only

Per-ticket worked spans for the board's piano-roll Timeline view, in one read pass. For every ticket returns: created date, startedAt (first status→In Progress audit event, falling back to its earliest work-log entry, then createdDate — startedSource says which), completedAt (completionDate or last status→Done event), lastActivity, status/product/type/sprint/priority/model for lane grouping and colour, cumulative tokens/additions/deletions/cost, and per-day work rollups (days[]) for clip intensity. Also returns a board-wide byDate[] rollup (tokens/additions/deletions/cost per day) for the datastream overlay strip. Optional from/to (ISO date or datetime) keep only spans whose worked window overlaps that range. Read-only.

Inputs: project (required), to, from.

get_work_logGet work logA
Read-only

Read work-log entries, most-recent first. Optionally filter to one ticket. Returns entries plus a velocity rollup.

Inputs: project (required), limit, ticket.

get_work_packetGet work packetA
Read-only

Assemble a focused brief for one ticket before you work it: scope, linked-issue details, code location + custom project prompt, scratchpad mentions, the ticket's recent work log, files to read, and a definition of done. Read the files it points to rather than dumping them. When the project config etaHints is on (default), also carries an eta ({estimatedMinutes:{low,high}, basis}) so you can tell the human how long this ticket is expected to take (FBMCPF-269).

Inputs: ticket (required), project (required).

graduate_projectGraduate projectA
Destructive

One-command incubator → dedicated-repo graduation (lifecycle "Option C"). Copies the project's CODE out to targetPath, EXCLUDING pad files (featurelist/buglist/scratchpad/etc) and junk (node_modules, .git, *.log, .zip, tmp_, ...), then repoints codeLocation, sets stage=graduated and gitTargets.codeRepo, and records the move in the scratchpad. The pad STAYS in the boards dir — it is only read, never modified or deleted — and the target repo additionally gets a read-only snapshot mirror of the pad files under .featureboard/. When commit is on and git is available the copied code + mirror are git-init'd (if needed) and committed; git absence/failure is tolerated as a warning. DRY-RUN BY DEFAULT: apply is false unless you pass apply:true, so the first call returns the plan (source, target, files, skipped) without touching the filesystem. CADSolver was the manual prototype.

Inputs: project (required), targetPath (required), apply, commit, +1 more.

import_tasksImport tasksA

Import a backlog from raw text into a board. Accepts a markdown checklist (- [ ] Title: desc), CSV (with a header row: title, description, product, priority, type, due, labels, status), or a JSON array/object ({features:[…], bugs:[…]} or a flat array). Format is auto-detected. Set dryRun to preview the parsed tasks without writing them.

Inputs: content (required), project (required), dryRun, format, +1 more.

leads_mapLeads mapB
Read-only

Geographic + pipeline rollup for the leads map: mappable points (leads with lat/lng), counts by status and by city, geocoded/ungeocoded tally, and total pipeline value. Rendering is left to the board or a generated report.

Inputs: project (required).

license_statusLicense statusA
Read-only

Report the current licensing state: usage tier, whether writes are allowed, and (for a commercial trial) time remaining. Call this if a write was blocked, or during onboarding.

Inputs: no named parameters.

list_bookingsList bookingsA
Read-only

List bookings for the board, newest-first. Filter by company or status ('scheduled'/'cancelled'), or pass upcoming:true for scheduled future bookings sorted soonest-first.

Inputs: project (required), status, company, upcoming.

list_campaignsList campaignsA
Read-only

List marketing campaigns (newest-first) with summary stats (recipients, opens, open rate, batch count).

Inputs: project (required), status.

list_code_filesList code filesA
Read-only

List files and folders under the project's codeLocation (optionally a subpath), with sizes and extensions. Skips vendor/build dirs (node_modules, .git, dist, …). depth controls how many levels to expand. Sandboxed to codeLocation.

Inputs: project (required), depth, subpath.

list_companiesList CRM companiesA
Read-only

List the project's CRM companies (id, name, domain, contact count, products), alphabetical by name. Pass product to show only companies associated with that product.

Inputs: project (required), product.

list_contract_templatesList contract templatesA
Read-only

List the standard contract templates (NDA, MSA, SOW, commercial license) with their required fields.

Inputs: no named parameters.

list_crm_inboxList CRM inboxA
Read-only

List CRM inbox messages (newest-first), optionally filtered by status (pending/approved/rejected), company, and/or type (support/sales/contact/feedback/other).

Inputs: project (required), type, status, company.

list_decisionsList architecture decision recordsA
Read-only

Read a project's ADR log as structured entries: id, title, date, context, decision, consequences, tickets. Pass ticket to filter to decisions relevant to that ticket.

Inputs: project (required), ticket.

list_kb_docsList kb docsA
Read-only

List a board's kb/ docs: slug, title, updatedAt, size, and a short excerpt of each (not the full body — use get_kb_doc for that).

Inputs: project (required).

list_lead_areasList lead areasA
Read-only

List the defined geographic lead areas (id, name, centre, radius).

Inputs: project (required).

list_leadsList leadsA
Read-only

List leads (newest-first), optionally filtered by pipeline status and/or company.

Inputs: project (required), status, company.

list_mailList mailA
Read-only

List mail (newest-first), optionally filtered by status (draft/sent) and/or company. Sent items form the mail history.

Inputs: project (required), status, company.

list_mediaList media assetsA
Read-only

List a project's media gallery: images and shareable HTML reports in its media/ folder. Each asset carries enough to render a visual grid — kind, mimeType, sizeBytes + sizeLabel + sizeBucket, image dimensions (width/height, parsed from file headers), a preview reference (inline text snippet for reports, a get_media src for images), plus sidecar metadata (title, tags, brandWords, linked ticket). Read-only; returns an empty gallery if the project has no media/ folder yet. Optionally filter by kind.

Inputs: project (required), kind.

list_media_commentsList media commentsA
Read-only

List an asset's comments, both as a flat array and as a threaded tree (root comments with nested replies).

Inputs: name (required), project (required).

list_pagesList website pagesA
Read-only

List the site's pages: the home page (site/index.html) plus each sub-page with its slug, title, and file.

Inputs: project (required).

list_projectsList projectsA
Read-only

List all boards (projects) under the configured boards folder.

Inputs: no named parameters.

list_referencesList reference uploadsA
Read-only

List the reference/source images under media/uploads/ (inputs for generation).

Inputs: project (required).

list_review_commentsList review commentsA
Read-only

List review comments for a project, optionally scoped to one ticket, with their resolved state. Set includeResolved:false to see only open feedback.

Inputs: project (required), ticket, includeResolved.

list_sharesList social share draftsA
Read-only

List saved share drafts (newest-first), optionally filtered by asset and/or platform.

Inputs: project (required), asset, platform.

list_site_assetsList website assetsB
Read-only

List the assets stored under the site's assets/ folder (name, ref, size).

Inputs: project (required).

list_site_templatesList starter site templatesA
Read-only

List the available starter website templates (landing, docs, blog) the builder can start from.

Inputs: no named parameters.

list_sourcesList research sourcesA
Read-only

List a board's sources/ library: slug, title, source, url, linked ticket, tags, dates, size, and a short excerpt of each (not the full raw text — use get_source for that).

Inputs: project (required).

list_sprintsList sprintsA
Read-only

List a board's sprints (config registry plus any label-only sprints) with progress per sprint (total/done/inProgress/todo, complete flag) and the count of open backlog tickets in no sprint.

Inputs: project (required).

list_tasksList tasksA
Read-only

List features and/or bugs on a board, most-recent first. Filter by type, status, product, label, or search. Returns a compact one-line-per-ticket view by default and is paginated (limit/offset) so large boards don't blow the context budget — set compact:false for full details, and raise limit or page with offset to see more. Use get_metrics for a pure overview.

Inputs: project (required), ref, type, label, +7 more.

list_test_pagesList test pagesA
Read-only

List the standalone HTML test pages under test-pages/.

Inputs: project (required).

list_test_variantsList multi-model test variantsA
Read-only

List the per-model test variants present for a ticket (test/..test.js) and which model tiers cover it. Reads the project's test/ dir under its code location; feeds the multi-model eval (FBMCPF-148).

Inputs: ticket (required), project (required).

list_variationsList a variation groupA
Read-only

List the gallery assets that share a variation group id (alternatives generated from one prompt), for side-by-side review.

Inputs: group (required), project (required).

list_worktreesList a project's git worktreesA
Read-only

List the git worktrees for a project's code repo (git worktree list). Each entry carries its path, branch, HEAD, whether it's the main repo working tree (isMain), and the derived ticket id. Also returns the resolved worktreeDir where per-ticket worktrees live (OUTSIDE the repo by default; see the sync caveat on create_worktree). Read-only.

Inputs: project (required).

log_bugLog bugA

Log a bug to a board's buglist.md. Returns the new ticket (FBB-###).

Inputs: title (required), project (required), ref, labels, +8 more.

log_heartbeatLog a dispatch heartbeatA

Append a lightweight in-flight progress ping for a ticket a sub-agent is actively working: a phase/milestone note, and optionally the model, elapsed minutes, and tokens spent so far. Distinct from log_work (which records a completed unit of work at the end of a session) — heartbeats are informational pings emitted DURING a long (5-13min) dispatch, so get_agent_monitor and the board's live/stall banners have something to show besides a generic "multitasking" indicator until the sub-agent returns. Call it at a few natural milestones (e.g. "read the ticket + adjacent code", "wrote the fix", "tests passing, writing report") rather than on every tool call. Sub-agents may call this directly — it is informational only and does not move the ticket's status.

Inputs: note (required), ticket (required), project (required), model, +2 more.

log_test_runLog test runA

Record a test run's result (passed/failed/skipped, optional suite + ticket + summary) to the board's test_runs.md. You run the tests (e.g. via the shell); this stores the report so the board can surface pass/fail over time.

Inputs: project (required), suite, failed, passed, +3 more.

log_workLog workA

Append a work event to the board's work log: a summary plus optional tokens, additions/deletions, and model, tied to a ticket. Feeds velocity and health.

Inputs: project (required), summary (required), model, ticket, +5 more.

mark_email_sentMark an email sentB

Record that a draft was sent (moves it into mail history with a sentAt timestamp). Does not actually send — tracking only.

Inputs: id (required), project (required).

next_taskNext task to workA
Read-only

Return the next open ticket to work (status Todo or In Progress), so you can pull work one item at a time. Prefers In Progress, then earliest due date, then oldest ticket. Returns null when the board is clear. When the project config etaHints is on (default), also carries an eta estimate for the returned ticket (FBMCPF-269).

Inputs: project (required), type.

next_waveNext wave of work (fill every lane)A
Read-only

The PLURAL of next_task: return the whole dispatchable set at once, already partitioned into file-disjoint lanes, so every sub-agent lane can be filled in ONE call instead of N sequential next_task round-trips. Use this — not repeated next_task — whenever you are working a board with more than one open ticket. lanes[] are mutually file-disjoint and safe to run as CONCURRENT sub-agents; tickets WITHIN a lane share files and must run serially in the order given. sequential[] holds orchestrator-only tickets (fable) that run inline. Each ticket carries its own dispatch block ({subAgent, model, cap, parallelizable, instruction}) so no second lookup is needed. Pass occupied with the tickets your sub-agents are still working and call it again to REFILL just the lanes that freed up — lanes containing a running ticket come back under busyLanes and are never re-served. stopCondition is the authority on whether the loop is over: an empty wave is a steer_project event, NOT a stop. FBMCPF-392 multi-user: tickets other users have In Progress come back under heldByOthers (never in your lanes), and lanes sharing files with their tickets are withheld as busyLanes with heldBy — wave paths stay disjoint across users with zero prompts.

Inputs: project (required), type, maxLanes, occupied, +1 more.

notify_slackNotify SlackA

Post a message to THIS project's user-configured Slack incoming webhook. This is deliberate outbound egress: the board is otherwise local-only, and this sends to the https://hooks.slack.com/... URL the user set in project config (slackWebhook) — nowhere else. No-ops with sent:false when Slack is unconfigured or the event isn't in the project's slackEvents allow-list; failures return a warning and never throw.

Inputs: text (required), project (required), event.

open_pull_requestOpen a PR for a ticket's branchA

Turn a ticket's pushed ticket/ branch into a pull request with a ticket-linked title and a closing-keyword body (Closes ) — the last step of the worktree→review loop after create_worktree + commit_feature. Uses the gh CLI when installed; otherwise returns a pre-filled compare URL to open manually. If the branch isn't on origin yet it is pushed first only when the resolved git mode is commit-push. Never throws for environmental gaps (no remote, no gh, unpushed branch) — returns opened:false with a reason.

Inputs: ticket (required), project (required), base, draft.

pad_syncSync the projectpad over gitA
Idempotent

Explicitly sync the board's pad repo(s): action "status" reports each pad repo's dirty file count, ahead/behind vs the remote, and last push/pull age; "push" commits everything dirty under the pad paths and pushes (rejected pushes pull --rebase and retry once); "pull" pull --rebases the pad from the remote immediately (ignores the rate limit). Automatic syncing (FBMCPF-395) normally makes this unnecessary — claims push instantly, other writes push debounced, dispatch reads pull first — but use it to verify sync state, force a flush before ending a session, or recover after being offline. Monorepo-safe: pads inside a shared workspace repo are committed at the enclosing repo root, scoped to the pad paths.

Inputs: action, project.

plan_budgetPlan budgetA
Read-only

Map a token budget onto the priority-ordered open queue BEFORE spending it: assigns tickets to days (greedy load-balance), draws the cutline where the budget runs out, and reports the Opus/Sonnet split with blended cost units. Optionally restrict to one sprint. When account-wide planLimits is captured (set_global_config), also returns an additive blendPlan (FBMCPF-279): days to reset, the fable/non-fable percent-per-day pace that converges both weekly meters, and concrete parallel-wave suggestions sized from the open backlog's effort and the board's historical tokens-per-ticket. The token budgeting is unchanged. Read-only — apply model choices with update_task labels if you want them stuck.

Inputs: project (required), days, sprint, budgetTokens.

plan_workPlan work (break a request onto the board)A

Turn a user request into board items in one step. Optionally creates the project, then adds the features and bugs you list. Use this as the FIRST step when starting a substantive request, then work the tickets one at a time. Returns all created tickets. When the project config etaHints is on (default), each created ticket carries an eta estimate and the response carries a totalEta roll-up (FBMCPF-269).

Inputs: project (required), bugs, features, createProject, +1 more.

post_project_updatePost project updateA

Append a dated narrative status update (Linear-style) to the project's updates.md pad — a lightweight health check-in that lives between the heavier sprint close-out reports. Takes a health flag (on-track | at-risk | off-track) and a free-text narrative. The latest update (and a staleness hint when it's more than 7 days old) is surfaced on get_metrics and get_health. When the project config voiceLint is on, the narrative is scored for AI-writing tells and the result is attached as voice (warn-only, never blocks the update).

Inputs: health (required), project (required), narrative (required).

predict_due_datesPredict due datesA
Read-only

Estimate when open work will complete by dividing the backlog by the board's observed throughput (tickets closed per active day). Walks the priority-ordered queue to give each open ticket a projected completion date, suggests a due date for tickets that don't have one, and flags tickets whose existing due date is likely to slip. Read-only — apply a suggestion with update_task if you want it stuck.

Inputs: project (required), asOf, type.

prepare_researchPrepare research requestA
Read-only

FBMCPF-263: deterministically assemble a research REQUEST packet for a ticket BEFORE implementation (no model calls). Returns the questions to answer — how to execute (approaches + tradeoffs), prior art IN THIS repo (files/tickets), comparables/competitors, risks/invariants — plus local sources to seed from (matching KB docs, docs/ paths, code hints, and prior-art hits from the local lexical RAG, FBMCPF-264), a deliverable spec (a collated markdown brief ≤ ~150 lines), a saveInstruction (orchestrator saves the returned brief via add_kb_doc as research/ so getWorkPacket auto-attaches it as researchBrief), and a suggested cheap model (haiku for effort:low/medium, else sonnet). When the research phase resolves OFF (config researchOnIntake:false or a research:off label) returns { skip:true, reason }; a research:on label forces it on.

Inputs: ticket (required), project (required).

prune_boardPrune board ticketsA
Destructive

Guarded cleanup: deletes ONLY the ticket ids you pass, and only when confirm is true (otherwise returns a dry-run preview of what would be deleted). Non-existent ids are reported, not fatal. Pair with scan_board_cleanup's suggestedRemovals.

Inputs: project (required), tickets (required), confirm.

publish_media_to_sitePublish a media asset to the siteA

Publish a gallery asset as a page on the project site (media/push-to-blog). A report/HTML/text asset becomes the page's content; an image is copied to site/assets and shown on the page. Returns the new page. Links media → website.

Inputs: name (required), project (required), slug, title.

read_code_fileRead a code fileA
Read-only

Read a file under the project's codeLocation as UTF-8 text (size-capped; binary files are flagged, not dumped). Returns content + line count. Sandboxed to codeLocation (no path escape).

Inputs: path (required), project (required), maxBytes.

record_campaign_openRecord a campaign openA
Idempotent

Record that a recipient opened a campaign (idempotent per recipient) — for when a mail connector or manual entry reports opens. Updates open-rate stats.

Inputs: id (required), email (required), project (required).

record_dispatchRecord a dispatch handoffA

Record who is actively working an In Progress ticket: appended as a 'dispatch' audit event (ticket_events.jsonl), so get_agent_monitor's lastDispatch and the board UI's orchestration chip can show whether a ticket is running on a sub-agent or back with the orchestrator. Call this right after set_status "In Progress" when handing a ticket off to a fresh sub-agent — worker:"sub-agent", with model (sonnet/opus/haiku/fable) and parallel:true when it's running alongside other sub-agent dispatches. Call it again with worker:"orchestrator" when you take the ticket back (e.g. for review before commit) — the newest call always wins as the ticket's current lastDispatch. Informational only: it never moves the ticket's status.

Inputs: ticket (required), worker (required), project (required), note, +2 more.

record_learningRecord a canonical learningA
Idempotent

Record a durable, re-usable truth discovered while working — an API gotcha, an invariant, a constraint, a design decision confirmed in code (e.g. 'OCC fillets need edge ids re-resolved after every boolean'). One TOPIC = one canonical note (kb/learning-.md): calling again with the same topic REPLACES the body — latest confirmed truth wins, no appended contradictions; git keeps the history and the frontmatter accumulates ticket provenance. Use this for knowledge the NEXT ticket needs, not work narration (that's log_work) and not in-flight research (that's append_research). Learnings are indexed like any kb doc: they surface in search_kb, rag_search, and are auto-injected into matching work packets.

Inputs: topic (required), content (required), project (required), ticket.

register_emailRegister onboarding email (optional)A
Idempotent

Store an email address the user explicitly typed and submitted on the tier-picker onboarding screen (the 'Save email' action — separate from picking a usage tier), then POST it once to the featureboard.ai registrations listener. This is deliberate outbound egress: the board is otherwise local-only, and this is the only call it makes without a user-configured destination (contrast notify_slack, which requires a webhook the user pastes in). There is no usage telemetry — only this email, and only after explicit submit. Never call this speculatively (e.g. on every onboarding render, or with an unconfirmed/autofilled value); omit or pass an empty string to skip. No-ops (no local write, no network call) when email is empty or malformed. Safe to call again later — once posted, it will not re-POST.

Inputs: email (required).

remove_annotationRemove a media annotationA
Destructive

Remove an annotation from an asset by its id (from get_media). Returns the remaining count.

Inputs: id (required), name (required), project (required).

remove_attachmentRemove attachmentB
DestructiveIdempotent

Detach a previously attached file path or URL from a ticket.

Inputs: ticket (required), project (required), attachment (required).

remove_company_agreementRemove a company agreementC
Destructive

Delete a contract/license from a company by id.

Inputs: id (required), company (required), project (required).

remove_contactRemove a CRM contactB
Destructive

Remove a contact from a company by its contact id (e.g. c1).

Inputs: company (required), contact (required), project (required).

remove_media_commentRemove a media commentA
Destructive

Remove a comment by id (from get_media / list_media_comments). By default its reply subtree is removed too; set cascade:false to refuse when it still has replies. Returns the ids removed.

Inputs: id (required), name (required), project (required), cascade.

remove_pageRemove a website pageC
Destructive

Delete a sub-page (by slug) and its rendered file. The home page can't be removed this way.

Inputs: slug (required), project (required).

remove_productRemove productA
DestructiveIdempotent

Remove a product from a board's product list (existing ticket tags are left as-is).

Inputs: name (required), project (required).

remove_shareRemove a social share draftA
Destructive

Delete a share draft by its id (from list_shares).

Inputs: id (required), project (required).

remove_test_pageRemove a test pageA
Destructive

Delete a test page by name.

Inputs: name (required), project (required).

repair_duplicate_idsRepair duplicate ticket idsA
Idempotent

Find ticket ids that appear more than once on a board (legacy data can carry collisions like FBF-491 twice), and optionally renumber the later occurrences to fresh ids. Dry-run by default; pass apply:true to write. Note: updates to a duplicated id are refused until the board is repaired.

Inputs: project (required), apply.

report_company_bugLog a company-reported bugA

Log a bug reported by a company: creates a board bug (FBB-###), links it to the company, and records the report on the company. Ties customer reports to the bug workflow.

Inputs: title (required), company (required), project (required), description.

request_commercial_licenseRequest a commercial licenseA

Start the commercial licensing process. Records the request locally (for the licensor's CRM) and returns the licensing URL and email to complete a signed agreement. After the licensor issues a key, use activate_license.

Inputs: name (required), email (required), company (required), notes, +1 more.

resolve_company_bugResolve a company-reported bugA
Idempotent

Mark a company-reported bug resolved: sets the board bug to Done and flips the company's report entry to resolved.

Inputs: ticket (required), company (required), project (required).

resolve_review_commentResolve review commentA
Idempotent

Mark a review comment resolved by its id (RC-). Idempotent. Once every comment on a ticket is resolved it stops surfacing in the work packet and (if in Review) leaves next_task's queue.

Inputs: id (required), project (required).

revert_mediaRevert a media assetA

Restore a prior version of an asset as the current one. The current copy is archived first, so the revert is itself undoable. Use get_media to find the version id.

Inputs: name (required), project (required), version (required).

review_crm_messageReview a CRM inbox messageA
Idempotent

Approve or reject a pending CRM inbox message by id. Records the decision and timestamp.

Inputs: id (required), project (required), decision (required).

routing_scorecardRouting scorecardA
Read-only

Which model tier should actually run your tickets, measured instead of guessed (FBMCPF-351). Scores every Done ticket from data the board already keeps — work-log tokens + model, ticket_events status transitions, and bugs filed with ref: — and reports, per tier: closed tickets, median tokens, median $ cost, median cycle time (In Progress -> Done), rework rate (reopened, or a follow-up bug filed after close-out), and the headline COST PER CLEAN TICKET (dollars per ticket that stayed closed). Cross-cut by effort:low/medium/high so the answer is 'which tier for THIS size of ticket', not one global average. A tier with fewer than minSamples closed tickets gets NO verdict — the readout says 'insufficient data' with the sample count rather than guessing. Advice only: it never writes a model:/cap: label, so intake stays deterministic. Pair with plan_budget (what the queue will cost) and daily_plan (what to run today). Returns the per-tier and per-effort STATS by default; the per-ticket evidence rows are opt-in via includeRows (a mature board has hundreds and they blow the result cap).

Inputs: project (required), rowLimit, minSamples, windowDays, +1 more.

save_generated_testSave generated test variantsA
Read-only

Ingest the model-generated test variants for a ticket (submit them as variants: [{model, content}]). Tags each with its model, dedupes identical/near-identical assertions across variants (whitespace + variable names normalized; a fully-duplicate test block is dropped and noted), and returns the runnable files to write (test/..test.js) plus a queryable manifest (test/.variants.json). Read-only: it returns file contents for you to write.

Inputs: ticket (required), project (required), variants (required).

save_mediaSave media assetA

Save a generated asset into a project's media/ folder — a shareable HTML report (or SVG) as UTF-8 text, or an image as base64 (encoding:'base64'). You generate the content; this persists the bytes plus a .meta.json sidecar (title, prompt, tags, linked ticket, generatedAt) that list_media reads back. Name must be a plain filename with an extension, e.g. q3-report.html.

Inputs: name (required), content (required), project (required), tags, +6 more.

save_packaging_configSave packaging configA
Idempotent

Persist the .mcpb packaging metadata for a project (packaging.json): name (slugified), displayName, description, longDescription, keywords, version. Validated by the same rules the build preflight uses; rejects hard errors (missing name/description). Only provided fields change.

Inputs: project (required), name, version, keywords, +3 more.

save_test_pageSave a test pageA
Idempotent

Create/overwrite a standalone HTML test/QA page under the project's test-pages/ folder.

Inputs: html (required), name (required), project (required).

scaffold_siteScaffold a whole website from one specA

Generate a whole site in one shot from a single spec instead of set_site field-by-field: sets the home page (title, tagline, theme, sections) and creates each initial sub-page. Persisted through the website store and rendered to the site location (/site/ by default, or the project's websiteLocation when set). Pass initGit:true to give the scaffolded site its own git repo (git init + a first "site: scaffold" commit) when it is not already inside one — the repo path is returned. Pair with the generate_site prompt, which has Claude produce the spec.

Inputs: title (required), project (required), pages, theme, +3 more.

scan_board_cleanupScan board for cleanupA
Read-only

Read-only deep-clean scan: finds likely-duplicate tickets (grouped by title similarity, each group nominating a keeper + removal candidates), stale/placeholder tickets (old Todo items, placeholder titles), open tickets missing a model:/cap: label (FBMCPF-159 intake orchestration guard — nothing should sit in the queue without a sub-model orchestration decision), and priority-scaled SLA breaches (FBMCPF-198: high-priority tickets stuck In Progress with no recent work-log activity → 'escalate'; tickets languishing in Todo → 'stale'; per-priority thresholds overridable via the slaThresholds config key). Returns a suggested removal set to feed prune_board. Never deletes — a good fit for a recurring Cowork scheduled task that surfaces breaches each morning.

Inputs: project (required), staleDays, similarity.

scan_test_cleanupScan tests for cleanupA
Read-only

Read-only deep-clean of the project's test/ dir: finds byte-identical duplicate test files, stale files whose filename ticket id is no longer on the board, and empty stub files (only TODO placeholder assertions). Returns a suggested removal set. Never deletes — companion to scan_board_cleanup.

Inputs: project (required).

search_kbSearch kb docsA
Read-only

Keyword search across a board's kb doc titles + content, ranked (title hits weighted above content hits). Returns matches with a short excerpt around the first hit and the doc's path. This is the same matcher get_work_packet uses to inject relevant docs into a ticket's packet (kbMatches).

Inputs: query (required), project (required), limit.

search_mediaSearch media assetsB
Read-only

Search/filter a project's media gallery by kind, by exact tag, and/or a free-text query matched across asset name, title, tags, and the generation prompt. Returns matching assets with metadata.

Inputs: project (required), tag, kind, query.

set_analytics_configConfigure external analyticsA
Idempotent

Configure which external analytics provider to READ site traffic from (distinct from set_site_analytics, which injects tracking). Provider is plausible/umami/custom (Google Analytics needs an OAuth connector). No API key is stored — the read proxy reads it from the FEATUREBOARD_ANALYTICS_KEY env var. Set enabled:false to turn the proxy off.

Inputs: project (required), host, period, siteId, +4 more.

set_brandingSet project brandingA
Idempotent

Set the project's brand kit in one place — name, tagline, brand words, voice/tone, primary & accent colors, logo, and font — so every generated asset (media, website, campaigns) stays consistent. Stored on the board config; retrieve it with get_branding. By default also applies colors/font to the project website if one exists.

Inputs: project (required), font, logo, name, +6 more.

set_company_productsSet a company's productsA
Idempotent

Record which products a company uses/owns (replaces the list; de-duplicated). Surfaced on the company record and usable via list_companies(product=...).

Inputs: company (required), project (required), products (required).

set_git_configConfigure git integrationA
Idempotent

Enable/configure optional per-project git integration so finished tickets can be committed (and optionally pushed) to the project's code repo. No secrets are stored — push uses the machine's own git credentials. Set codeLocation in project config to point at the repo. gitMode ("commit-only" | "commit-push" | "ask") controls what commit_feature/deploy_site do when a call doesn't pass an explicit push param, and overrides the account-wide default from set_global_config for this project only.

Inputs: project (required), push, branch, remote, +3 more.

set_global_configConfigure account-wide settingsA
Idempotent

Set FeatureBoard's account-wide settings, applied to every project that doesn't set its own override via set_git_config. gitMode — "commit-only" (never push automatically; the original default behavior), "commit-push" (push after every commit_feature/deploy_site that doesn't pass an explicit push param), or "ask" (commit only, and return a note asking the caller to confirm with the user before pushing — never pushes silently). planLimits — the two weekly Claude-Max usage meters that reset together ({fablePct, allModelsPct, capturedAt (ISO), resetAt (ISO), targetRatio (default 1.0)}); pass it after reading the usage tab so the board can steer both meters to exhaust at the same reset (blend tracking, FBMCPF-278/279). Pass planLimits:null to clear it. Ask the user about gitMode during onboarding.

Inputs: gitMode, padSync, telemetry, planLimits, +1 more.

set_handoffSet ticket handoff noteA
DestructiveIdempotent

Write a ticket's handoff note (handoffs/.md): free-form markdown for whatever a successor ticket needs to know. Overwrites any existing note. Surfaces automatically in the work packets of tickets blockedBy this one; read it via get_work_packet.

Inputs: note (required), ticket (required), project (required).

set_lead_statusSet lead statusA
Idempotent

Move a lead along the pipeline (new/contacted/qualified/won/lost). Records the update time.

Inputs: id (required), status (required), project (required).

set_page_seoSet a page's SEO metadataA
Idempotent

Set SEO for the home page (omit slug, or slug='index') or a sub-page: meta description, Open Graph title/description/type, and image. Re-renders the page. Merges over existing SEO.

Inputs: project (required), slug, image, ogType, +3 more.

set_project_configSet project configA
Idempotent

Update a board's settings (only provided fields change). Writes to the MCP-managed config; never mutates legacy project_config.json. codeLocation points the code tools at the project's source repo; websiteLocation points the website tools (get_site/set_site/add_page/deploy_site/scaffold_site/...) at the project's SHIPPED site, which may live outside the pad in its own repo (absolute path to the assets dir) — leave it unset to keep the site under /site/. Also configures voiceLint/voiceLintMin/voiceProfile (AI-writing-tell self-checks on drafting tools) and the etaHints dispatch toggle.

Inputs: project (required), goal, ragK, stage, +28 more.

set_requirementsSet ticket requirementsA
DestructiveIdempotent

Write a ticket's refined requirements pad (requirements/.md): intent, assumptions, acceptance criteria, and open questions. Overwrites any existing pad. Once set, the ticket's work packet carries these requirements and its definition-of-done becomes the acceptance criteria. Draft the content first (see the refine prompt), then persist it here.

Inputs: intent (required), ticket (required), project (required), assumptions, +2 more.

set_scratchpadSet scratchpadA
DestructiveIdempotent

Overwrite a board's scratchpad.md with new content. Use append_scratchpad to add a note without replacing existing content.

Inputs: content (required), project (required).

set_siteBuild/update the project websiteB

Set the project's splash site (title, tagline, theme light/dark, and sections). Re-renders site/index.html. Only provided fields change.

Inputs: project (required), seo, theme, title, +2 more.

set_site_analyticsConfigure site analyticsA
Idempotent

Add an analytics snippet to every page of the site's : Plausible or Google Analytics by id, or a raw custom . Re-renders the site. Set enabled:false to remove it.

Inputs: project (required), id, enabled, snippet, +1 more.

set_standardSet the project standard (rigor profile)A
Idempotent

Set — and LOCK — how much rigor a project's work is held to. Levels: "prototype" (move fast, minimal ceremony), "standard" (normal professional loop), "polished" (research-first: competitor teardowns, layout/IA of comparable apps, white papers, UX/UI heuristics, automation-everywhere, high test rigor + self-review). The resolved standard is injected into every work packet (packet.standard + extra definition-of-done items) and bends research-on-intake (polished forces it on with expanded questions; prototype skips it). mandate is the project's own free-text bar, carried verbatim into packets. INFERENCE RULE: when a project's standard is unset/unlocked, infer the level from the user's cues ONCE (pass source:"inferred") and lock it. A locked standard is settled — this tool refuses to change it unless force:true, which you pass ONLY when the user explicitly asks to change the standard. Account-wide default for unset projects: set_global_config defaultStandard.

Inputs: level (required), project (required), force, source, +1 more.

set_statusSet statusA
Idempotent

Move a task between Todo / In Progress / Review / Done. Review sits between In Progress and Done when requireReview is on; approve:true overrides the gate. When moving to Done you can also record structured completion metadata (model, tokens, additions, deletions) — these are written to the work log and roll up into velocity/metrics. For graduated projects, moving to Done also refreshes the pad snapshot in /.featureboard/ (best-effort; a mirror failure never blocks the status change). If git is enabled for the project and Done is reached with no commit referencing the ticket (recorded via commit_feature, or found via git log --grep), the response carries uncommitted:true + a commitReminder — or, when requireCommitOnDone is on, the move is refused outright (approve:true overrides). FBMCPF-392 multi-user: moving to In Progress stamps [Owner: ] on the ticket (identity auto-resolved — FEATUREBOARD_USER, then git config user.name, then OS username); promoting a ticket another user has In Progress is refused unless force:true takes it over. Ownership releases on Todo/Done and syncs with the pad through git.

Inputs: status (required), ticket (required), project (required), force, +11 more.

set_usage_typeSet usage type (onboarding)A
Idempotent

Record how FeatureBoard is being used. 'personal' = private non-commercial (free). 'public' = public/open-source/nonprofit non-commercial (free). 'commercial-trial' = start a free 24-hour commercial evaluation (writes freeze after 24h). 'commercial' = commercial use (requires a license key via activate_license). Ask the user which applies before setting.

Inputs: type (required).

start_checksStart background static checksA

Fire-and-forget: spawn a DETACHED background run of the project's static checks (syntax-check of changed .js/.mjs/.cjs via node --check, plus any configured commands — lint, a fast test subset, etc.) and return a runId IMMEDIATELY. Pure CPU, zero model tokens, never blocks — the runner survives this call and writes its results to /checks/.json. Scope it to a commit with revision (else it uses the last commit / dirty tree). Poll results later with get_check_results. commit_feature already starts checks automatically on every commit (checks.autoOnCommit); use this to run them on demand. Returns started:false with a reason when the project has no checks config and no package.json in its code repo.

Inputs: project (required), ticket, revision.

steer_projectSteer the project (next wave when the queue runs dry)A

FBMCPF-317: the churn loop's answer to an empty queue — call this when next_task returns nothing (or the user asks to 'keep improving'). Returns ordered, executable passes that encode the owner's steering pattern: (1) REVIEW the Done tickets completed since the last steering pass — adversarial defect hunt over their diffs (get_ticket_diff semantic:true, churn_reconcile), file log_bug for real defects; (2) TIGHTEN — triage the attached cleanup/strengthen findings into tickets or dismissals; (3) RESEARCH toward the project's goal at its locked standard (polished standards carry the competitor/layout/whitepaper/UX question set) grounded in rag_search prior art, then add_feature the next wave; (4) RESUME next_task. Review candidates are claimed in steering.json so the same work is never re-reviewed. If actionable is false twice in a row, report to the user and stop — do not spin. Pass dryRun:true to preview without claiming.

Inputs: project (required), dryRun.

submit_crm_intakeSubmit a support/contact requestA

Capture an inbound support or contact submission (support-info / crm-submit) into the CRM inbox, pending review. Records the requester (name/email), a category (support/sales/contact/feedback/other), an optional related company, and the message; synthesizes a subject if none is given.

Inputs: message (required), project (required), name, type, +3 more.

suggest_file_splitSuggest a file split (refactor prompt)A
Read-only

Given an oversized source file (see code_file_map's splitCandidates), return a structured, ready-to-execute refactor proposal: exported symbols clustered by name-prefix, proposed target modules, keep-original-as-barrel guidance, and a prompt to hand straight to the agent. Read-only — the server never edits code; Claude executes the split.

Inputs: file (required), project (required).

suggest_packagingSuggest packaging metadataA
Read-onlyIdempotent

AI-gen seed: derive a draft of the .mcpb packaging metadata (name, displayName, description, keywords) from the project's config, brand, and products. Returns a draft to refine — it does NOT save. Refine it, then persist with save_packaging_config.

Inputs: project (required).

suggest_test_stubSuggest test stubA
Read-only

Generate a boilerplate test file (path + node:test content) for a ticket, derived from its title/description and the board's code location. Agent-native 'fixtest': call it when creating or starting a ticket, then write the returned file. Read-only — it returns the stub, it does not create the file.

Inputs: ticket (required), project (required).

tag_mediaTag a media assetA

Add and/or remove custom tags on a media asset (updates the sidecar only — the asset bytes and version history are untouched). Tags are de-duplicated. Returns the asset's new tag list.

Inputs: name (required), project (required), add, remove.

test_runs_by_suiteTest runs grouped by suiteA
Read-only

Organize recorded test runs (from log_test_run) by suite: each suite's latest result, run count, cumulative pass/fail, and pass-rate, plus the list of currently-failing suites. Surfaces coverage/health per suite instead of a flat list.

Inputs: project (required).

ticket_customersCustomers linked to a ticketA
Read-only

Reverse lookup: which CRM companies a board ticket is linked to (surfaces the ticket↔customer relationship).

Inputs: ticket (required), project (required).

update_company_agreementUpdate/extend a company agreementA
Idempotent

Update a company contract/license by id — e.g. extend a license (new expiresAt), change status ('signed'/'renewed'/'expired'), seats, term, or value.

Inputs: id (required), company (required), project (required), term, +4 more.

update_contactUpdate a CRM contactA
Idempotent

Edit a contact on a company (only provided fields change). Pass an empty string to clear email/role/phone.

Inputs: company (required), contact (required), project (required), name, +3 more.

update_lead_locationUpdate a lead's locationA
Idempotent

Set a lead's coordinates (lat/lng) and/or city, so it maps correctly and falls into the right areas.

Inputs: id (required), project (required), lat, lng, +1 more.

update_taskUpdate taskB
Idempotent

Update fields on an existing task. Only provided fields change.

Inputs: ticket (required), project (required), ref, title, +11 more.

upload_referenceUpload a reference imageB

Save a reference/source image under media/uploads/ (base64) to use as input for media generation — kept separate from the gallery. Reference it in a generate/refine prompt so Claude or an image model can work from it.

Inputs: name (required), content (required), project (required), encoding.

upload_site_assetUpload a website assetA

Store an image/asset under the site's assets/ folder (base64 by default, or utf8 text). Returns a ref like 'assets/logo.png' to use in page sections. Name must be a plain filename with an extension.

Inputs: name (required), content (required), project (required), encoding.

validate_feedbackValidate feedback (raw text -> candidate tickets)A

Parse unstructured feedback (user notes, review comments, bug reports) into candidate tickets, each with a suggested type (feature/bug), product, and priority from deterministic keyword heuristics only — no model calls. DRY-RUN BY DEFAULT (apply:false, the default): returns the structured candidate list for you to review/edit; creates NOTHING. Always dry-run first. When ready, call again with apply:true to bulk-create the candidates (optionally pass back an edited candidates array — e.g. from the dry-run response with corrected type/product/priority/title — instead of re-parsing feedback).

Inputs: project (required), apply, feedback, candidates.

validate_packagingValidate packaging metadataA
Read-onlyIdempotent

Run the build-preflight packaging checks against the project's saved packaging.json: reports hard errors (missing/invalid name or description) and advisory warnings (no keywords, missing displayName/longDescription).

Inputs: project (required).

voice_lintVoice lint (AI-writing-tell scorer)A
Read-only

Score text for AI-writing tells (overused lexical items like "delve"/"tapestry", contrastive-pivot rhetoric like "not just X, but Y", sycophantic openers, tidy-summary closers, and rhythm/density metrics: sentence-length burstiness, tricolon density, em-dash density, bolded-list density) using the research-backed ruleset in docs/VOICE-RESEARCH.md. Intended for editing YOUR OWN outbound drafts before sending them (project updates, docs, customer replies) — not for judging whether someone else's writing was AI-written. Pass project to apply that project's voiceProfile config (extraBannedPhrases, allowedTells, samplesNote) on top of the base ruleset; threshold (default 30) only changes the summary wording, not which findings fire.

Inputs: text (required), project, threshold.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 217 tools

    Disambiguation2/5

    While many tools are highly specialized, there is significant overlap across domains: set_site vs scaffold_site vs apply_site_template vs add_page vs edit_site_section all mutate site content, add_feature vs add_features_bulk vs plan_work vs import_tasks vs validate_feedback all create tickets, and list_tasks/get_task/get_board overlap in board views. Tools like get_metrics/export_metrics/export_tasks also have overlapping read purposes, forcing agents to carefully parse descriptions to choose correctly.

    Naming Consistency3/5

    The dominant pattern is verb_noun (add_feature, list_media, set_status, get_kb_doc, remove_contact), but there are notable deviations: noun-first names (customer_portal, leads_map, routing_scorecard, license_status, bug_impact_scan), missing verbs (coverage_by_product, test_runs_by_suite), and abbreviation mixing (get_rag_explorer vs get_kb_doc, eval_report vs get_metrics). Most names are readable, but the inconsistent ordering and verb styles create a mixed convention.

    Tool Count1/5

    217 tools is extreme for any single MCP server. The server appears to be a monolithic all-in-one business toolkit (board, CRM, media, website, email, campaigns, licensing, git, analytics, testing, RAG, packaging), each of which could be its own server. Even with a wide scope, no agent can efficiently discover or select from 217 tools, and the context cost alone makes the set unwieldy.

    Completeness4/5

    Within each subdomain the coverage is quite thorough: tickets have create/read/update/delete/status/sprint/attachment/comments, the CRM has companies/contacts/leads/bookings/agreements, the website has page/section/SEO/template/asset/analytics operations, and testing has generate/save/list/run/coverage flows. Minor gaps exist (e.g., no update_media/replace_media for assets, no campaign deletion, no direct email send), but the surface is generally deep enough to avoid dead ends.

    Maintenance

    ActivityNo data
    ResponsivenessSyncing

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables agents to read and drive a local-first Kanban board for issue tracking, allowing them to list, create, update, and resolve issues from Claude Code sessions.
      7 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables Claude Code to manage a terminal-based Kanban board with tools for task CRUD, moving, completing, archiving, and board initialization and export/import.
      22 npm
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Manages feature documentation and bug tracking inside an Obsidian vault, organized by project, enabling project listing, feature doc writing, bug filing, status updates, and retrieval.
      9
      17 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables Claude to search, read, write, and manage a local markdown vault through 8 tools, turning your notes into an AI-accessible knowledge base.
      3 npm
      AGPL 3.0