AI导哈

Favro项目管理MCP服务器

一个将 Favro 项目管理能力接入 AI 助手的 MCP 服务，通过 API 提供看板、卡片、标签、用户和评论等管理功能，适用于在 Claude、Cursor、VS Code 等开发环境中用自然语言操作项目任务。

  • by truls27a
  • Python
  • 本地部署
  • 5 星标
  • 更新于
在 GitHub 查看 truls27a/favro-mcp

使用说明

Favro MCP

MCP server for interacting with Favro project management.

Installation

pip install favro-mcp

Getting Your Favro API Token

  1. Log in to Favro
  2. Click your username (top-left corner)
  3. Select My Profile
  4. Go to API Tokens
  5. Click Create new token
  6. Give it a name (e.g., "Favro MCP") and click Create
  7. Copy the token — you won't be able to see it again!
Setup for Claude Code 
claude mcp add --transport stdio favro \
  -e FAVRO_EMAIL=your-email@example.com \
  -e FAVRO_API_TOKEN=your-token \
  -- favro-mcp

See Claude Code MCP documentation for more details.

Setup for Claude Desktop

Add the following to your claude_desktop_config.json (~/Library/Application Support/Claude/ on macOS, %APPDATA%\Claude on Windows):

{
  "mcpServers": {
    "favro": {
      "command": "/full/path/to/favro-mcp",
      "env": {
        "FAVRO_EMAIL": "your-email@example.com",
        "FAVRO_API_TOKEN": "your-token-here"
      }
    }
  }
}

Finding the full path: Claude Desktop doesn't inherit your shell's PATH, so you need the absolute path to favro-mcp:

# macOS/Linux (with pip)
which favro-mcp

# Windows (PowerShell)
(Get-Command favro-mcp).Source

Then restart Claude Desktop.

See Claude Desktop MCP documentation for more details.

Setup for Cursor

Add the following to your Cursor MCP configuration file:

  • Global (all projects): ~/.cursor/mcp.json
  • Project-specific: .cursor/mcp.json in your project root
{
  "mcpServers": {
    "favro": {
      "command": "favro-mcp",
      "env": {
        "FAVRO_EMAIL": "your-email@example.com",
        "FAVRO_API_TOKEN": "your-token-here"
      }
    }
  }
}

You can also open the MCP settings via Command Palette: Cmd+Shift+P (Mac) or Ctrl+Shift+P (Windows) → search "MCP" → select "View: Open MCP Settings".

After configuration, use Agent mode in Cursor's AI chat to access Favro tools.

See Cursor MCP documentation for more details.

Setup for VS Code

Add the following to .vscode/mcp.json in your workspace:

{
  "servers": {
    "favro": {
      "type": "stdio",
      "command": "favro-mcp",
      "env": {
        "FAVRO_EMAIL": "your-email@example.com",
        "FAVRO_API_TOKEN": "your-token-here"
      }
    }
  }
}

Use Agent mode in GitHub Copilot Chat to access Favro tools.

See VS Code MCP documentation for more details.

Setup for Codex CLI

Add the following to ~/.codex/config.toml:

[mcp_servers.favro]
command = "favro-mcp"

[mcp_servers.favro.env]
FAVRO_EMAIL = "your-email@example.com"
FAVRO_API_TOKEN = "your-token-here"

Or add via CLI:

codex mcp add favro \
  --env FAVRO_EMAIL=your-email@example.com \
  --env FAVRO_API_TOKEN=your-token \
  -- favro-mcp

See Codex MCP documentation for more details.

Tools

Organizations

Tool Description
list_organizations List all organizations
get_current_organization Get current organization
set_organization Set active organization

Users

Tool Description
list_users List users, filter by name or email
get_user Get a user by ID, name, or email

Collections (Folders)

Tool Description
list_collections List all collections (folders)

Boards

Tool Description
list_boards List boards
get_board Get board with columns
get_current_board Get current board
set_board Set active board

Cards

Tool Description
list_cards List cards on board
get_card_details Get card details
add_comment Add a comment to card
create_card Create a card
update_card Update a card
move_card Move card to column or another board, or reorder it in a column
assign_card Assign/unassign user
tag_card Add/remove tag
delete_card Delete a card
list_custom_fields List custom fields

Tags

Tool Description
list_tags List tags, filter by name

Columns

Tool Description
list_columns List columns on board
create_column Create a column
rename_column Rename a column
move_column Move column position
delete_column Delete a column

Lanes (Swimlanes)

Tool Description
list_lanes List lanes (swimlanes) on board

Lanes themselves are read-only in the Favro API (no create/rename/delete). To place a card in a lane, pass its ID or name as the lane argument to create_card, update_card, or move_card (use list_lanes to discover them).

Development

This project uses uv for development.

Setup

  1. Install uv:

    macOS / Linux:

    curl -LsSf https://astral.sh/uv/install.sh | sh

    Windows (PowerShell):

    powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

  2. Clone the repository:

    git clone https://github.com/truls27a/favro-mcp.git
cd favro-mcp

  3. Install dependencies:

    uv sync --dev

Running from Source

To run a local/modified version instead of the published package:

{
  "mcpServers": {
    "favro": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/favro-mcp",
        "python",
        "-m",
        "favro_mcp"
      ],
      "env": {
        "FAVRO_EMAIL": "your-email@example.com",
        "FAVRO_API_TOKEN": "your-token-here"
      }
    }
  }
}

Related

  • lh-etals/favro-mcp — a Go rewrite of this project with a single-binary installer, wider tool coverage, and multi-client auto-configuration.

相关 MCP