Skip to main content
Glama
valentil

FeatureBoard MCP Server

by valentil

Set project config

set_project_config
Idempotent

Update a project board's settings—code location, website path, voice lint, pricing, and more—without changing unprovided fields.

Instructions

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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
goalNoThe project's north star outcome, e.g. 'become the default agent-run task board; grow paid seats'. Injected into work packets and aimed at by steer_project's research pass.
ragKNoFBMCPF-264: how many RAG chunks to attach to a work packet (default 5).
stageNoProject lifecycle stage (FBMCPF-149).
checksNoFBMCPF-261: async background static-check config. Checks run DETACHED on every commit (pure CPU, zero model tokens) so the orchestrator can commit and immediately keep working, then collect results with get_check_results. When absent but the code repo has a package.json, a cheap syntax-only default applies.
pricingNoFBMCPF-157: per-model $/MTok overrides merged over the built-in defaults (server/pricing.js DEFAULT_PRICING, sourced from current Anthropic API pricing). Keyed by model tier ("fable" | "opus" | "sonnet" | "haiku" | "default"); only the fields you provide change, the rest keep their default. blendedPerMTok is used as a fallback rate for work-log entries that only logged a single total token count (no input/output split).
projectYes
websiteNo
etaHintsNoAppend an ETA reminder to dispatch instructions for steps expected to exceed ~2 minutes. Default on.
productsNo
doneGatesNoFBMCPF-215: per-project preconditions on → Done — require no unresolved review comments, a passing logged test run, and/or a work-log entry for the ticket. Each toggle independent, all off by default; approve:true overrides.
imageToolNoPreferred image-generation tool/connector/skill name for generate_image (e.g. an image MCP or an 'imagegen' skill). If unset, generate_image uses any available image generator, else falls back to SVG.
voiceLintNoFBMCPF-267/268: turn on AI-writing-tell self-checks (voice lint) for drafting tools like draft_share and post_project_update; results attach as a warn-only `voice` key on the response. Default off.
agentModelNo
brandTitleNoBoard display title (branding).
brandVoiceNoBrand voice/tone for generated media, e.g. 'confident, playful, plain-spoken'.
brandWordsNoBrand / trial words woven into generated media (e.g. product name, taglines, campaign phrases).
gitTargetsNoExplicit commit destinations: code, projectpad, and the shipped website can each live in different repos (FBMCPF-149, FBMCPF-249). websiteRepo is otherwise inferred by walking up from websiteLocation to its .git root.
descriptionNo
slackEventsNoWhen on, a ticket must pass through Review before it can be marked Done (set_status enforces the gate; approve:true overrides).
codeLocationNo
customPromptNoProject-specific guidance injected into every work packet.
ragInPacketsNoFBMCPF-264: attach top-k local lexical RAG chunks (BM25 over KB/docs/ticket-history) to every work packet as ragChunks. Zero tokens, zero network. Default true.
slackWebhookNoProject's https://hooks.slack.com/... webhook; null clears. Opt-in egress.
voiceLintMinNoFBMCPF-267/268: voiceScore threshold above which a voice-lint warning is attached (default 25). Only used when voiceLint is on.
voiceProfileNoFBMCPF-267: project-specific tuning for the voice-lint ruleset used when voiceLint is on.
brandSubtitleNoBoard subtitle / byline (branding).
requireReviewNo
websiteLocationNoAbsolute path to the project's SHIPPED website assets dir (may be outside the pad, in its own git repo). When set, all website tools operate there instead of <project>/site/ (FBMCPF-249).
researchOnIntakeNoFBMCPF-263: run an optional research phase before implementing a ticket — cheap haiku/sonnet sub-agents collate approaches/prior-art/comparables/risks into a brief for the implementing model. Defaults ON when unset (resolved in code, not force-written). Per-ticket escape hatch: a research:off label skips it, research:on forces it.
sprintAutoAssignNoFBMCPF-219: auto-assign un-slotted new tickets to the active sprint — off (default), priority (priority <= 2 only), or all. An explicit sprint: label always wins.
requireChecksOnDoneNoFBMCPF-261: when on, set_status refuses to move a ticket to Done if its latest background static-check run FAILED (approve:true overrides). A still-running run does not block — it just adds a note. Default false.
requireCommitOnDoneNoWhen on and git is enabled for the project, set_status refuses to move a ticket to Done unless a commit references it (recorded via commit_feature or found via git log --grep); approve:true overrides. Default false — a plain non-blocking uncommitted/commitReminder warning otherwise.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate idempotent and not destructive; description adds that only provided fields change and never touches legacy config. Also explains side effects on other tools (e.g., websiteLocation affects site tools). No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single long paragraph (around 200 words) conveys all needed info but lacks structure. Could be broken into bullet points or sections for easier parsing by an agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 32 parameters, nested objects, and no output schema, the description is fairly comprehensive. Covers return behavior implicitly (no output schema), side effects, and parameter interdependencies. Missing error cases or prerequisites, but acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 78% (high), so baseline 3. Description adds practical context beyond schema, e.g., 'codeLocation points the code tools at the project's source repo' and explains interactions between parameters like websiteLocation and site tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States clearly: 'Update a board's settings (only provided fields change).' Specific verb and resource, distinct from sibling get_project_config. Mentions important fields like codeLocation, websiteLocation, voiceLint, etc.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states that it writes to MCP-managed config and never mutates legacy config. Gives guidance on websiteLocation (leave unset for default). Does not explicitly list alternatives like set_branding or set_global_config, but context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/valentil/featureboard-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server