
MCP Linear
A Model Context Protocol server that enables AI assistants to interact with Linear project management systems, allowing users to create, update, and manage issues, projects, teams, and comments through natural language.
README
<p align="center"> <img src="https://github.com/tacticlaunch/mcp-linear/blob/main/docs/linear-app-icon.png?raw=true" alt="Linear App Icon" width="250" height="250"> </p>
MCP Linear
A Model Context Protocol (MCP) server implementation for the Linear GraphQL API that enables AI assistants to interact with Linear project management systems.
<a href="https://glama.ai/mcp/servers/@tacticlaunch/mcp-linear"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@tacticlaunch/mcp-linear/badge" /> </a>
Features
MCP Linear bridges the gap between AI assistant and Linear (project management tool) by implementing the MCP protocol. This allows to:
- Retrieve issues, projects, teams, and other data from Linear
- Create and update issues
- Change issue status
- Assign issues to team members
- Add comments
- Create projects and teams
Example prompts
Once connected, you can use prompts like:
- "Show me all my Linear issues"
- "Create a new issue titled 'Fix login bug' in the Frontend team"
- "Change the status of issue FE-123 to 'In Progress'"
- "Assign issue BE-456 to John Smith"
- "Add a comment to issue UI-789: 'This needs to be fixed by Friday'"
Installation
Authentication
MCP Linear now uses Nango for secure authentication. You'll need to configure the following environment variables:
NANGO_CONNECTION_ID
: Your connection ID from NangoNANGO_INTEGRATION_ID
: Your integration ID from NangoNANGO_BASE_URL
: The base URL for Nango API (typicallyhttps://api.nango.dev
)NANGO_SECRET_KEY
: Your secret key from Nango
Fallback Authentication
If Nango is not configured, the system will fall back to using a Linear API token passed via the --token
command line argument.
Installing via Smithery (Recommended)
- To install MCP Linear for Cursor:
npx -y @smithery/cli install @tacticlaunch/mcp-linear --client cursor
- To install MCP Linear for Claude Desktop:
npx -y @smithery/cli install @tacticlaunch/mcp-linear --client claude
Manual Configuration
Add the following to your MCP settings file:
{
"mcpServers": {
"linear": {
"command": "npx",
"args": ["-y", "@tacticlaunch/mcp-linear"],
"env": {
"NANGO_CONNECTION_ID": "your_connection_id",
"NANGO_INTEGRATION_ID": "your_integration_id",
"NANGO_BASE_URL": "https://api.nango.dev",
"NANGO_SECRET_KEY": "your_secret_key"
}
}
}
}
Client-Specific Configuration Locations
- Cursor:
~/.cursor/mcp.json
- Claude Desktop:
~/Library/Application Support/Claude/claude_desktop_config.json
- Claude VSCode Extension:
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- GoMCP:
~/.config/gomcp/config.yaml
Manual run
Prerequisites
- Node.js (v18+)
- NPM or Yarn
- Nango configuration or Linear API token
# Install globally
npm install -g @tacticlaunch/mcp-linear
# Or clone and install locally
git clone https://github.com/tacticlaunch/mcp-linear.git
cd mcp-linear
npm install
npm link # Makes the package available globally
Running the Server
Create a .env
file with your Nango configuration:
NANGO_CONNECTION_ID=your_connection_id
NANGO_INTEGRATION_ID=your_integration_id
NANGO_BASE_URL=https://api.nango.dev
NANGO_SECRET_KEY=your_secret_key
Then run the server:
mcp-linear
Or use the fallback method with a Linear API token:
mcp-linear --token YOUR_LINEAR_API_TOKEN
Available Tools
See TOOLS.md for a complete list of available tools and planned features.
Development
See DEVELOPMENT.md for more information on how to develop locally.
Links
tacticlaunch/cursor-memory-bank - If you are a developer seeking to enhance your workflow with Cursor, consider giving it a try.
License
This project is licensed under the MIT License - see the LICENSE file for details.
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。