返回 MCP 目录
public公开dns本地运行

Linear MCP工具

通过模型上下文协议,启用与 Linear 的 API 交互,以编程方式管理问题、团队和项目。

article

README

Linear MCP Server

Note: This is a custom implementation. For the official Cline Linear MCP server, see cline/linear-mcp.

A Model Context Protocol (MCP) server that provides tools for interacting with Linear's API, enabling AI agents to manage issues, projects, and teams programmatically through the Linear platform.

Features

  • Issue Management

    • Create new issues with customizable properties (title, description, team, assignee, priority, labels)
    • List issues with flexible filtering options (team, assignee, status)
    • Update existing issues (title, description, status, assignee, priority)
  • Team Management

    • List all teams in the workspace
    • Access team details including ID, name, key, and description
  • Project Management

    • List all projects with optional team filtering
    • View project details including name, description, state, and associated teams

Prerequisites

  • Node.js (v16 or higher)
  • A Linear account with API access
  • Linear API key with appropriate permissions

Quick Start

  1. Get your Linear API key from Linear's Developer Settings

  2. Run with your API key:

LINEAR_API_KEY=your-api-key npx @ibraheem4/linear-mcp

Or set it in your environment:

export LINEAR_API_KEY=your-api-key
npx @ibraheem4/linear-mcp

Development Setup

  1. Clone the repository:
git clone [repository-url]
cd linear-mcp
  1. Install dependencies:
npm install
  1. Build the project:
npm run build

Running with Inspector

For local development and debugging, you can use the MCP Inspector:

  1. Install supergateway:
npm install -g supergateway
  1. Use the included run.sh script:
chmod +x run.sh
LINEAR_API_KEY=your-api-key ./run.sh
  1. Access the Inspector:
    • Open localhost:1337 in your browser
    • The Inspector connects via Server-Sent Events (SSE)
    • Test and debug tool calls through the Inspector interface

Configuration

Configure the MCP server in your settings file based on your client:

For Claude Desktop

  • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "linear-mcp": {
      "command": "node",
      "args": ["/path/to/linear-mcp/build/index.js"],
      "env": {
        "LINEAR_API_KEY": "your-api-key-here"
      },
      "disabled": false,
      "alwaysAllow": []
    }
  }
}

For VS Code Extension (Cline)

Location: ~/Library/Application Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json

{
  "mcpServers": {
    "linear-mcp": {
      "command": "node",
      "args": ["/path/to/linear-mcp/build/index.js"],
      "env": {
        "LINEAR_API_KEY": "your-api-key-here"
      },
      "disabled": false,
      "alwaysAllow": []
    }
  }
}

For Cursor (cursor.sh)

For Cursor, the server must be run with the full path:

node /Users/ibraheem/Projects/linear-mcp/build/index.js

Available Tools

create_issue

Creates a new issue in Linear.

{
  title: string;          // Required: Issue title
  description?: string;   // Optional: Issue description (markdown supported)
  teamId: string;        // Required: Team ID
  assigneeId?: string;   // Optional: Assignee user ID
  priority?: number;     // Optional: Priority (0-4)
  labels?: string[];     // Optional: Label IDs to apply
}

list_issues

Lists issues with optional filters.

{
  teamId?: string;      // Optional: Filter by team ID
  assigneeId?: string;  // Optional: Filter by assignee ID
  status?: string;      // Optional: Filter by status
  first?: number;       // Optional: Number of issues to return (default: 50)
}

update_issue

Updates an existing issue.

{
  issueId: string;       // Required: Issue ID
  title?: string;        // Optional: New title
  description?: string;  // Optional: New description
  status?: string;      // Optional: New status
  assigneeId?: string;  // Optional: New assignee ID
  priority?: number;    // Optional: New priority (0-4)
}

list_teams

Lists all teams in the workspace. No parameters required.

list_projects

Lists all projects with optional filtering.

{
  teamId?: string;     // Optional: Filter by team ID
  first?: number;      // Optional: Number of projects to return (default: 50)
}

get_issue

Gets detailed information about a specific issue.

{
  issueId: string; // Required: Issue ID
}

Development

For development with auto-rebuild:

npm run watch

Error Handling

The server includes comprehensive error handling for:

  • Invalid API keys
  • Missing required parameters
  • Linear API errors
  • Invalid tool requests

All errors are properly formatted and returned with descriptive messages.

Technical Details

Built with:

  • TypeScript
  • Linear SDK (@linear/sdk v37.0.0)
  • MCP SDK (@modelcontextprotocol/sdk v0.6.0)

The server uses stdio for communication and implements the Model Context Protocol for seamless integration with AI agents.

License

MIT

help

运行方式说明

cloud

托管运行

托管运行通常表示这个 MCP Server 由服务方环境承载,用户一般按页面提供的连接方式或授权流程接入,不需要在本地长期启动一个 MCP 进程

  1. 打开服务方连接页
  2. 完成授权或复制端点
  3. 在 MCP 客户端中连接
terminal

本地运行 / 其它方式

本地运行通常需要用户在自己的电脑或服务器上安装依赖,把 server_config 复制到 MCP 客户端,并按 env_schema 补齐环境变量、密钥或其它配置

  1. 复制 server_config
  2. 安装所需依赖
  3. 补齐环境变量后重启客户端