weeek-mcp

weeek-mcp

Read-only MCP server for the Weeek Public API. Use it from Cursor or Claude Code to browse projects, search tasks, read attachments, and (with a browser session) load task comments.

Category
Visit Server

README

weeek-mcp

Read-only MCP server for the Weeek Public API. Use it from Cursor or Claude Code to browse projects, search tasks, read attachments, and (with a browser session) load task comments.

Features

Can Cannot
Projects, boards, columns, tasks Weeek Docs / Wiki (not in Public API)
Search / filter tasks, my open tasks Writes (not shipped; opt-in later)
Members & tags PDF/DOCX text extract (v1: URL / text files only)
Attachments: images + txt/md/json/csv
Task comments via imported browser session Comments are not in Public API

“Documents” here means task attachments, not Weeek Docs.

Requirements

  • Node.js ≥ 20
  • Weeek API token (Workspace settings → API)

Install

git clone https://github.com/prod-broke-again/weeek-mcp.git
cd weeek-mcp
npm install
npm run build

Optional: refresh vendored OpenAPI with npm run fetch:openapi, then npm run generate:dto.

Configuration

Copy .env.example and set at least WEEEK_API_TOKEN. Never commit .env or session cookies.

Variable Required Default Notes
WEEEK_API_TOKEN yes — Workspace API token
WEEEK_DEFAULT_PROJECT_ID no — Used when tools omit projectId
WEEEK_PROJECT_ALIASES no — e.g. portal:4,ecd:7
WEEEK_READ_ONLY_PROJECTS no all Whitelist of project ids
WEEEK_ALLOW_WRITE no false Write tools not shipped in v1
WEEEK_MAX_ATTACHMENT_BYTES no 8388608 8 MiB
WEEEK_CACHE_TTL_SECONDS no 300 Directory/project cache
WEEEK_RPS no 4 Client-side rate limit
WEEEK_LOG_LEVEL no info Logs go to stderr only
WEEEK_BASE_URL no https://api.weeek.net/public/v1 Public API
WEEEK_APP_BASE_URL no https://api.weeek.net Private app API host
WEEEK_SESSION_FILE no ~/.weeek-mcp/session.json Browser session store
WEEEK_SESSION_COOKIE no — Optional cookie override
WEEEK_WORKSPACE_ID no — Needed if cookie string has no workspace_id

Cursor / Claude Code

Example Cursor MCP config (~/.cursor/mcp.json or project .cursor/mcp.json):

{
  "mcpServers": {
    "weeek": {
      "command": "node",
      "args": ["/absolute/path/to/weeek-mcp/dist/bin/weeek-mcp.js"],
      "env": {
        "WEEEK_API_TOKEN": "your-token",
        "WEEEK_DEFAULT_PROJECT_ID": "2",
        "WEEEK_READ_ONLY_PROJECTS": "2"
      }
    }
  }
}

More examples: examples/mcp.cursor.json, examples/mcp.claude.json.

Tools

  1. weeek_context — start here (sessionComments: ready|missing)
  2. weeek_auth_status — session check + import instructions
  3. weeek_session_import — paste session JSON
  4. weeek_list_projects
  5. weeek_get_project
  6. weeek_get_board
  7. weeek_search_tasks
  8. weeek_my_tasks
  9. weeek_get_task — card + comments when session is ready
  10. weeek_get_task_comments — comments only
  11. weeek_get_task_tree
  12. weeek_read_attachment
  13. weeek_list_members
  14. weeek_list_tags

Typical flow: context → (auth_status / session_import if needed) → search_tasks → get_task → read_attachment.

Task comments (browser session)

Public API has no comments. The web app loads them from:

GET https://api.weeek.net/ws/{workspaceId}/tm/tasks/{taskId}?withSubtasks=1

with session cookies. weeek_session is HttpOnly, so document.cookie cannot see it.

Import once

  1. Call weeek_auth_status (or open a task via weeek_get_task_comments).
  2. In https://app.weeek.net → DevTools → Network → open any task.
  3. Find api.weeek.net/ws/.../tm/tasks/... → Request Headers → Cookie → copy the value.
  4. Console: paste the helper from weeek_auth_status, then run
    weeekExportSession("PASTE_COOKIE_HERE")
    (or pass workspace id as the second argument).
  5. Paste the JSON into chat / call weeek_session_import.

Session is stored at ~/.weeek-mcp/session.json (Windows: %USERPROFILE%\.weeek-mcp\session.json).

Security: the cookie is a live login. Do not commit or share it. If leaked, log out of Weeek or rotate the password.

Development

npm test
npm run typecheck
npm run build
npm run dev   # stdio MCP via tsx

OpenAPI is vendored at openapi/weeek.json. Layout: domain → application → infrastructure → mcp.

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured