Feishu Project MCP server

Integrates with Feishu Project management API, enabling direct interaction with project data, tasks, and resources through environment variable authentication and stdio-based transport.
Back to servers
Provider
Roland0511
Release date
Mar 21, 2025
Language
Python
Package
Stats
3.4K downloads
3 stars

This MCP server provides a bridge for AI assistants to interact with Feishu (Lark) project management systems through the Model Context Protocol. It allows AI assistants to query, create, and manage work items in Feishu projects by wrapping Feishu's Open API functionality.

Installation

Prerequisites

You'll need a compatible MCP client such as:

More MCP clients can be found at: https://modelcontextprotocol.io/clients

Configuration

To configure the MCP server with Claude desktop client:

  1. Edit the Claude desktop configuration file:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
  2. Add the following configuration to the mcpServers field:

{
  "mcpServers": {
    "feishuproj": {
      "command": "uvx",
      "args": ["mcp-feishu-proj", "--transport", "stdio"],
      "env": {
        "FS_PROJ_PROJECT_KEY": "your_project_key",
        "FS_PROJ_USER_KEY": "your_user_key",
        "FS_PROJ_PLUGIN_ID": "your_plugin_id",
        "FS_PROJ_PLUGIN_SECRET": "your_plugin_secret"
      }
    }
  }
}
  1. Replace the environment variables with your actual Feishu project credentials:
    • FS_PROJ_PROJECT_KEY: Your Feishu project identifier
    • FS_PROJ_USER_KEY: Your user identifier
    • FS_PROJ_PLUGIN_ID: Your Feishu Open API plugin ID
    • FS_PROJ_PLUGIN_SECRET: Your Feishu Open API plugin secret

Supported Features

Authentication

  • Login and authentication flow

View Management

  • Get Feishu project view list
  • Get work items list for a view
  • Create fixed views
  • Update fixed views
  • Create conditional views
  • Update conditional views
  • Delete views

Work Item Management

  • Get work item details
  • Get metadata for creating work items
  • Create work items
  • Update work items
  • Batch update work item field values
  • Delete work items
  • Terminate/resume work items
  • Get work item operation records

Work Item Search

  • Get specified work item lists (single workspace)
  • Get specified work item lists (cross-workspace)
  • Get specified work item lists (single workspace with complex parameters)
  • Get specified work item lists (global search)
  • Get specified related work item lists

Attachment Management

  • Add attachments
  • Upload files
  • Download attachments
  • Delete attachments

Workspace Management

  • Get workspace list
  • Get workspace details
  • Get business line details under workspace
  • Get work item types under workspace
  • Get team members under workspace

User Management

  • Get user details
  • Search user list within tenant
  • Create custom user groups
  • Update user group members
  • Query user group members

Workspace Association

  • Get workspace association rule list
  • Get associated work item instance list under workspace association
  • Bind associated work item instance for workspace association
  • Unbind associated work item instance for workspace association

Process and Node Management

  • Get workflow details
  • Get workflow details (WBS)
  • Update nodes/scheduling
  • Complete/rollback nodes
  • State transitions

Process Configuration

  • Get workflow template list under work items
  • Get workflow template configuration details
  • Add workflow templates
  • Update workflow templates
  • Delete workflow templates

Subtasks

  • Get specified subtask list
  • Get subtask details
  • Create subtasks
  • Update subtasks
  • Complete/rollback subtasks
  • Delete subtasks

Comments

  • Add comments
  • Query comments
  • Update comments
  • Delete comments

Work Item Time Tracking

  • Get work item time record list
  • Create actual time entries
  • Update actual time entries
  • Delete actual time entries

Review Management

  • Batch query review opinions and conclusions
  • Modify review conclusions and opinions
  • Query review conclusion tags

Other Features

  • Add bots to groups
  • Get metric chart detailed data
  • Get process role configuration details

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later