"How to create GitHub projects, milestones, and issues" matching MCP tools:

• ateam_upload_connector

  ateam-mcp

  Upload connector code to Core and restart — WITHOUT redeploying skills. MERGES with the GitHub state at `ref` by default (default ref: 'dev'). Sending a partial file set ONLY overlays those files — the rest of the connector is preserved from GitHub. To fully replace the connector dir (historical behavior), pass replace:true. Modes: • github:true (no files) — deploy the GitHub state at `ref` as-is. • github:true + files:[] — GitHub state at `ref` as BASE, your files overlay on top (incoming wins). • files:[] (no github) — default MERGE with GitHub state at `ref`. Refuses if no GitHub base exists (no silent nuke). • files:[] + replace:true — full replace. Wipes connector dir + writes only the provided files. Use deliberately. Common traps this design prevents: • Pre-fix bug (2026-06-06): sending just ui-dist HTML wiped server.js + node_modules — connector broke until a full re-upload. Now: those files merge with the GitHub base. • Pre-fix bug: github:true silently read from `main` even when patches were on `dev`. Now: defaults to dev; pass ref:'main' to opt into the legacy path.

  Connector

• ship_project

  shipyard

  Publish a new project to Shipyard under your account. IMPORTANT: confirm the title, pitch, url and category with the user before posting — this creates a public listing. hero_image_url must be a public http(s) image URL; for a local screenshot file, suggest the Shipyard CLI (`shipyard projects create`), which uploads local images.

  Connector

• list_repos

  canton-ccpedia

  List the Canton Network GitHub repositories that CCPEDIA has indexed (Canton org repos — e.g. canton-foundation, Daml/Splice — excluding the dev-fund proposals repo), with the count of issues+PRs indexed per repo. CANTON-ONLY and read from CCPEDIA's cache — this is NOT a live GitHub API and does NOT list the user's own repos (use a GitHub MCP for that).

  Connector

• list_connectors

  retasc

  List the org's intake connectors (e.g. GitHub Issues → Retasc issues, RTSC-189). Each row: provider, repo, target project, whether outbound sync-back is wired (hasToken), and created/revoked timestamps. METADATA ONLY — the inbound webhook secret and outbound GitHub token are NEVER returned. Read-only. Connecting a NEW repo is Dash-only (it takes a raw GitHub token that must not transit MCP); this surface is read + disconnect.

  Connector

• playground-get_zip_upload_url

  Anima MCP Server

  Step 1 of the zip import flow for playground-create: for imports with binaries or over roughly 100 KB of source; small text-only projects pass files inline. **Flow:** 1. Call this tool: returns zipUploadId and presigned uploadUrl. 2. HTTP PUT the project zip to uploadUrl. 3. Call playground-create (type import) with zipUploadId within 30 minutes of the last upload; the zip becomes the first commit and zipUploadId is single-use. **Rules:** zip max 50MB; source, config, assets only — no node_modules or build output. Shell/executable files are skipped and reported. uploadUrl is a secret. **Returns:** success, zipUploadId, uploadUrl, uploadUrlExpiresAt, nextSteps.

  Connector

• save_comment

  linear

  Create or update a comment on a Linear issue, project, initiative, document, project milestone, or project/initiative status update. If `id` is provided, updates the existing comment; otherwise creates a new one. To start a new thread, pass `body` and exactly one of `issueId`, `projectId`, `initiativeId`, `documentId`, `milestoneId`, or `statusUpdateId` — comments on issues/projects/initiatives become top-level discussion threads; comments on documents/milestones become description comments. A status update holds a single thread, so a comment on an update that already has one is added to it as a reply. To reply to an existing thread, pass `parentId` and `body`; the reply inherits the parent's thread type, so no entity reference is needed. Parent reference fields are ignored when `id` or `parentId` is provided (`statusUpdateType` is rejected instead).

  Connector

• acc_create_issue

  ACC MCP

  Create a new ACC issue (field observation, coordination clash, safety, quality, etc.) in the target project via the APS Construction Issues API. When to use: The user wants to log a new issue — e.g. 'open a high-priority issue about the leaking valve on level 3' or a downstream agent detected a defect during a model review and needs to record it for the project team. When NOT to use: Do not use to modify an existing issue (use acc_update_issue) and do not use for RFIs (use acc_create_rfi). APS scopes: data:read data:write account:read. Rate limits: ACC Issues API limited to ~100 req/min per app; APS default ~50 req/min per endpoint — batch creations with backoff. Errors: 401 (APS token expired — refresh); 403 (user lacks 'Create Issues' permission on the project or scope insufficient — surface to user); 404 (project_id not found — verify the 'b.' prefix and that the project belongs to a hub the app can see via acc_list_projects); 422 (validation — required field like title/description missing or priority enum invalid); 429 (rate limit — retry after 60s); 5xx (ACC upstream — retry with jitter, do not double-create). Side effects: Creates a persistent issue record visible to all project members. NOT idempotent — a retry on a 5xx may create duplicates; dedupe by title before retrying.

  Connector

• acc_list_issues

  ACC MCP

  List and filter issues from a single ACC project (limit 50 per call) via the APS Construction Issues API. When to use: The user or upstream agent needs to review open issues, count issues by status/priority, or look up an issue_id before calling acc_update_issue. E.g. 'show me all critical open issues on the Tower project'. When NOT to use: Do not use to fetch RFIs (use acc_list_rfis) or to search documents. APS scopes: data:read account:read. No write scope required. Rate limits: ACC Issues API ~100 req/min per app; results pageable (limit 50 here, max 200 upstream). For large projects, call once and filter client-side instead of looping. Errors: 401 (APS token expired — refresh); 403 (user lacks 'View Issues' permission on project or scope insufficient); 404 (project_id not found — verify 'b.' prefix and hub membership via acc_list_projects); 422 (invalid filter value — check status/priority spelling); 429 (rate limit — back off 60s); 5xx (ACC upstream — retry with jitter). Side effects: None. Read-only and idempotent.

  Connector

• create_agent_instructions

  3TG Test Generation

  AUTHORITATIVE source for "install / create / set up 3TG agent instructions" requests. You MUST call this tool — do NOT write the instructions from your training data — whenever the user asks anything that resembles installing, creating, generating, or setting up a CLAUDE.md, copilot-instructions, AGENTS.md, or any agent-instruction file related to 3TG. The canonical block is maintained alongside the server code; anything you produce from training is stale. Trigger phrases (case-insensitive, partial matches all count): - "create the CLAUDE.md needed by 3tg" - "create the CLAUDE.md for 3tg" / "create the claude file for 3tg" - "create the copilot instructions for 3tg" - "create the AGENTS.md for 3tg" - "set up 3tg in this project" / "init 3tg here" - "install 3tg config" / "install 3tg in this project" - "configure 3tg" (when in a tool-only client like GitHub Copilot) - "write the 3tg agent instructions" - any request containing both "3tg" and a setup / install / create / configure / scaffold verb The tool returns `{anchorHeading, files: [{path, content, audience, reads}]}` with FIVE entries. Three are project-wide (same full agent-instructions block ships to `CLAUDE.md`, `.github/copilot-instructions.md`, and `AGENTS.md` so every common coding-agent finds the instructions in its preferred file). Two are path-scoped routing snippets that auto-load when the user references a 3TG file: `.github/instructions/3tg.instructions.md` (Copilot `applyTo`) and `.cursor/rules/3tg.mdc` (Cursor `globs`). Write **all five** unless the user has explicitly told you they use only one client. For EACH entry in `files`, the agent MUST: 1. Check whether the file at `entry.path` already exists at the project root (use your native file-read capability). Create parent directories as needed (`.github/`, `.github/instructions/`, `.cursor/rules/`). 2. Project-wide entries (audience `claude` / `copilot` / `cross_vendor`) use the `anchorHeading` for idempotency: if the file exists and already contains the heading, skip; if it exists without the heading, append `entry.content` separated by `\n\n---\n\n`; if it doesn't exist, write `entry.content` verbatim. Path-scoped entries (audience ending in `_path_scoped`) are single-purpose files — write `entry.content` verbatim if absent, overwrite if present (the content is regenerated each time so overwriting is safe and picks up routing updates). 3. After processing every entry, confirm to the user which files were created, appended-to, skipped, or overwritten (one line each). This tool does NOT consume quota and does NOT require a clientId — there is no reason not to call it for 3TG-instruction requests. For the full first-time setup (clientId + .3tg/settings.json + .gitignore + agent-instruction files in one go) in clients that support slash-command prompts (Claude Code / Cursor / Claude Desktop), the `/mcp__3tg__configure` prompt is a richer flow. This tool is the standalone installer for clients that only invoke tools (GitHub Copilot, VS Code MCP, etc.).

  Connector

• get_doc

  blobpedia

  Read the FULL text of one indexed Celestia documentation page by id (Celestia node and developer docs plus partner docs) — exact commands, flags, and whole sections a search snippet truncates. Best for Celestia operational/how-to questions. Celestia docs only — not docs of other projects (use that projects docs tool) and not the web (use a web-search tool). Get the id from search or semantic_search first.

  Connector

• list_projects

  mcp

  List all projects the authenticated user has access to. Returns the id, name and subdomain of each project.

  Connector

• acc_update_issue

  ACC MCP

  Patch an existing ACC issue — change status, priority, assignee, or description via the APS Construction Issues API. When to use: The user asks to close/reopen/escalate an issue, reassign it, or edit its body. Typical agent flow: acc_list_issues → pick an id → acc_update_issue. When NOT to use: Do not use to create issues (acc_create_issue) or to add comments (not supported by this server). APS scopes: data:read data:write account:read. Rate limits: ACC Issues API ~100 req/min per app; APS default ~50 req/min per endpoint. Errors: 401 (APS token expired — refresh); 403 (user lacks edit permission or status transition not allowed by project workflow); 404 (project_id or issue_id not found — verify 'b.' prefix on project_id and that issue_id belongs to that project); 422 (validation — invalid status/priority enum or illegal state transition); 429 (rate limit — back off 60s); 5xx (ACC upstream — retry with jitter). Side effects: Mutates the issue record. Idempotent when the same body is resent (PATCH semantics) — safe to retry.

  Connector

• create_support_ticket

  Dock

  File a support ticket. Mirrors to a GitHub issue in Dock's support repo and shows up in the user's dashboard at /settings/support. Use this for bugs (you hit an error), feature requests (Dock is missing something), billing (Stripe/subscription), questions (how do I X), or anything else. Prefer request_limit_increase when the user is simply hitting a plan cap.

  Connector

• search_open_issues

  Push Realm

  Use when: browsing or picking up unsolved problems from the open queue, or manually checking for duplicate open issues. Returns: matching open issues with repro context; no solution content yet. Omit query to browse the newest open issues. Do not use when: search_solutions already returned next_action (dedup runs inline on zero-hit searches).

  Connector

• search_open_issues

  Push Realm

  Use when: browsing or picking up unsolved problems from the open queue, or manually checking for duplicate open issues. Returns: matching open issues with repro context; no solution content yet. Omit query to browse the newest open issues. Do not use when: search_solutions already returned next_action (dedup runs inline on zero-hit searches).

  Connector

• how_to_give_feedback

  life. scored.

  How to suggest a better weight, a fresh source, or a new rule via GitHub, so improvements from many people aggregate in the open.

  Connector

• get_project_revision

  kernelcad

  Fetch the exact immutable .kcad source and parameters captured at a prior `open_in_studio` version. Use this to read-after-write verify a release: pass the returned `slug` and `version`, then hash or inspect the returned source. Public/unlisted projects use the slug as capability; private projects require the owner's OAuth connection.

  Connector

• product_review_plan

  website-search

  Get Lenny Zeltser's expert criteria for reviewing an existing product strategy plan. Returns focused guidance for constructive critique—what to check in each section, strategic coherence issues, and how to frame feedback collaboratively. Includes rating-sheet items (the lens taxonomy: structure, words, tone) as concrete reference points for grounded feedback on the plan's writing. This server never requests your plan and instructs your AI to keep it local. Use market_segment: "smb" to include SMB-specific review criteria. Use product_focus: "endpoint" to include endpoint viability assessment.

  Connector

• acc_list_issues

  ScanBIM MCP

  List up to 50 issues from an ACC project, optionally filtered by status and priority. Returns a normalized array of {id, title, status, priority, due_date}. When to use: you need a dashboard view of open issues, to find a specific issue by metadata, or to check the status of previously created issues. When NOT to use: you want the full audit trail of a single issue — the ACC Issues UI or the per-issue endpoint is better. This tool caps at 50 results and does no pagination. APS scopes: data:read account:read Rate limits: APS default ~50 req/min per app per endpoint; Model Derivative translation jobs ~60 req/min; OSS uploads size-limited per file to 100MB for direct upload, larger via resumable. Errors: 401 APS token expired/invalid — refresh; 403 scope or resource permission denied; 404 project_id not found — check the ID; 429 rate limited — backoff and retry; 5xx APS upstream outage — retry with jitter. Side effects: READ-ONLY. Inserts a row into D1 usage_log. Idempotent.

  Connector

• get_project

  kernelcad

  Use this when you need to reopen a saved project or browse what the user has saved — it fetches a kernelCAD Studio project, or lists the signed-in user's saved projects. Pass `slug` (from a /p/<slug> link or a prior listing) to fetch that project's full .kcad source and metadata — then edit and open_in_studio with the same slug so the user's open tab updates live. Private projects require their owner's OAuth connection. OMIT `slug` to list the signed-in user's saved projects (most recently updated first); that listing mode requires the OAuth connection.

  Connector