- Home
- MCP servers
- Linear MCP Integration Server
Linear MCP Integration Server
- typescript
0
GitHub Stars
typescript
Language
7 months ago
First Indexed
3 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"madebynando-mcp-linear-server": {
"command": "env",
"args": [
"LINEAR_API_KEY=your_linear_api_key",
"node",
"/path/to/your/mcp-linear-server/dist/server.js"
],
"env": {
"LINEAR_API_KEY": "your_linear_api_key_here"
}
}
}
}This MCP server enables Linear integration through the Model Context Protocol, allowing you to perform issue tracking and project management actions from your automated workflows. It exposes a set of tools that map directly to Linear operations, so you can create issues, search and filter them, retrieve sprint information, and manage teams and projects from your MCP client.
How to use
You interact with this server through an MCP client by calling named endpoints that correspond to Linear actions. Each tool represents a Linear operation, and you provide the required parameters (and any optional ones) to customize the request. The server handles authentication using your Linear API key and communicates with Linear to perform the requested task. Use this server to create issues, search issues with flexible filters, fetch current sprint issues, list teams and projects, and view workflow states for your Linear workspace.
How to install
Prerequisites: you need Node.js and npm installed on your machine. Ensure you have access to a Linear API key before proceeding.
# Copy the environment example and set your Linear API key
cp .env.example .env
# Install dependencies
npm install
# Development mode with auto-reload
npm run dev
# Production mode
npm start
# Build TypeScript
npm run build
# Run tests
npm run test
# Inspect MCP server
npm run inspect
Security and deployment notes
The server relies on a Linear API key for authentication. Keep this key secure and provide it to clients via environment configuration when starting the server. If you deploy with Docker, consider using a dedicated environment file and secure variable management. The server includes error handling, rate limiting, and automatic reconnection logic to maintain a stable integration with Linear.
Docker and containerized setup
You can run the application in Docker using the following approaches. The container can be started with an environment file containing your Linear API key or by providing the key in the start command.
# Build and run in detached mode
docker-compose up -d
# View logs
docker-compose logs -f
# Stop the container
docker-compose down
Using MCP commands with Cursor
If you are integrating with Cursor, you can register this MCP server using either a direct command or a Docker-based command as shown below.
# Direct command with API key (replace with your key and path)
env LINEAR_API_KEY=your_linear_api_key node /path/to/your/mcp-linear-server/dist/server.js
# Docker-based command (runs inside the existing container)
docker exec -i mcp-linear-server node dist/server.js
Tools exposed by this MCP server
This server provides a set of MCP tools that map to Linear operations. Each tool name corresponds to a Linear action you can perform through the MCP interface.
Available tools
linear_create_issue
Creates a new Linear issue with a title, mandatory teamId, and optional description, priority, and initial status.
linear_search_issues
Searches issues with optional filters such as query, teamId, status, assigneeId, priority, and a limit on results.
linear_sprint_issues
Retrieves all issues in the current sprint for a given team.
linear_search_teams
Finds teams by name or text query.
linear_filter_sprint_issues
Filters current sprint issues by status and narrows results to the current user.
linear_get_workflow_states
Returns all available workflow states (statuses) for a specified team.
linear_list_projects
Lists all Linear projects, optionally filtered by team and limited by a maximum number.