Weeek MCP server

weeek-mcp

A local MCP server for Weeek: projects, tasks and boards are read-only by default, writes are opt-in

  • 0 ★ on the repository
  • Last commit
  • MIT
MCP server

Extended access

Why this level

  • With READ_ONLY=false the agent can create, edit and move tasks in the workspace
  • The token grants access to everything its owner can see
All reasons and checks
Russian stack

yolkins/weeek-mcp

Install

Services

In your terminal, with SkillFoxx CLI

npx skillfoxx add mcp/weeek-mcp

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • With READ_ONLY=false the agent can create, edit and move tasks in the workspace
  • The token grants access to everything its owner can see

This is third-party code. Review the repository files before installing.

What it does

The server runs over stdio and uses a personal Weeek token to give an agent access to a workspace. Ten read tools are available by default: projects, tasks with filters and pagination, members, tags, boards and board columns. Five write tools, including creating and moving tasks, stay hidden until READ_ONLY is set to false, and can be narrowed further with an ENABLED_TOOLS allowlist. Responses are validated with zod, clipped to a character budget, and return distinct, agent-readable error codes.

Who it is for. For teams on Weeek who want an agent to see tasks and boards without risking changes by default.

Good fit when

  • You want an agent to read Weeek tasks, boards and members
  • You want a safe start with the option to enable specific writes later
  • You want to install via npx without building from source

Not a fit when

  • You need Weeek tools beyond tasks, projects and columns
  • You want to work without a personal API token

Example request

Show my open Weeek tasks for the redesign project

MCP

Transport
stdio
Authentication
API key

Environment variables

WEEEK_ACCESS_TOKEN required, secret
Personal Weeek API token
READ_ONLY
Hides the five write tools, defaults to true
ENABLED_TOOLS
Comma-separated allowlist of tool names

Limitations

You need a personal Weeek API token. Beyond the READ_ONLY flag itself, writes have no server-side confirmation step: task creation cannot be undone through the server, and moves or edits must be reverted by hand. The server does not read a .env file itself, so variables must come from the client's config.

How to disable. Remove the weeek entry from your MCP client configuration.

FAQ

Can the agent create tasks right after install?

No, the five write tools are not registered until READ_ONLY=false is set.

How do I limit the agent to one write action?

Set READ_ONLY=false and list the tool in ENABLED_TOOLS; the allowlist intersects with READ_ONLY rather than adding to it.

Discussion

No questions or reviews yet.

Russian stack

A 12-tool WEEEK MCP server split into 7 read and 5 write tools, so an MCP client can auto-approve the safe ones

MCP serverExtended access1Repository stars
Russian stack

Python MCP server for WEEEK API v1: tasks, projects, boards, funnels, deals and contacts, with SSE mode for n8n

MCP serverBroad access2Repository stars
Russian stack

A WEEEK MCP server that is read-only by default: tasks, attachments and comments via a browser session, writes are opt-in

MCP serverExtended access

WEEEK CLI and MCP on Bun

Weeek CLI + MCP Server

Russian stack

A weeek CLI command and an MCP server for WEEEK in one Bun package: projects, boards, tasks and subtasks from a terminal or an agent

MCP serverExtended access
Russian stack

A WEEEK MCP server creates a task from project, column and assignee names in one call, no chain of lookups for their IDs

MCP serverExtended access4Repository stars

README in short

The README covers npx install, a table of ten read tools and five write tools with what each one changes and how to undo it. It lists the environment variables in detail: token, base URL, timeout, READ_ONLY, ENABLED_TOOLS, response character limit and log level. There is a table of common startup errors and a section on MCP Inspector and local debugging.

README badge

Report a problem