Linear MCP server

This MCP server provides Linear integration capabilities through the Model Context Protocol, allowing AI models to interact with Linear for issue tracking and project management tasks.

Installation

To get started with the Linear MCP Integration Server, follow these steps:

Prerequisites

• Your Linear API key (available in Linear's settings > API section)
• Node.js installed on your system

Setting Up the Server

1. Create a .env file in the project root with your Linear API key:

LINEAR_API_KEY=your_api_key_here

2. Install dependencies:

npm install

3. Start the server:

# Development mode with auto-reload
npm run dev

# Production mode
npm start

Smithery Deployment

You can also deploy this server on Smithery.ai:

1. Create a Smithery.ai account
2. Add the repository to Smithery or claim an existing server
3. Configure the deployment with your Linear API key
4. Deploy the server

Available Tools

The server provides the following tools through the MCP interface:

Issue Management

Creating Issues

Use linear_create_issue with these parameters:

• title (required): Issue title
• teamId (required): Team ID to create issue in
• description (optional): Issue description (markdown supported)
• priority (optional): Priority level (0-4)
• status (optional): Initial status name

Searching Issues

Use linear_search_issues to find issues with these parameters:

• query (optional): Text to search in title/description
• teamId (optional): Filter by team
• status (optional): Filter by status
• assigneeId (optional): Filter by assignee
• priority (optional): Priority level (0-4)
• limit (optional, default: 10): Max results per page
• cursor (optional): Pagination cursor for fetching next page
• sortBy (optional, default: 'updated'): Field to sort by ('created', 'updated', 'priority', 'title')
• sortDirection (optional, default: 'desc'): Sort direction ('asc', 'desc')

Getting Issue Details

Retrieve detailed information about a specific issue with linear_get_issue_details:

• issueId (required): Issue ID (e.g., "DATA-1284") to fetch details for

Bulk Updating Status

Update multiple issues at once with linear_bulk_update_status:

• issueIds (required): List of issue IDs to update (e.g. ["ENG-123", "DATA-456"])
• targetStatus (required): Target status to set for all issues (e.g. "In Progress")

Sprint Management

Viewing Sprint Issues

Get all issues in the current sprint with linear_sprint_issues:

• teamId (required): Team ID to get sprint issues for

Filtering Sprint Issues

Filter current sprint issues with linear_filter_sprint_issues:

• teamId (required): Team ID to get sprint issues for
• status (required): Status to filter by (e.g. "Pending Prod Release")

Managing Cycles (Sprints)

Create, update, or get information about cycles with linear_manage_cycle:

• action (required): Action to perform: "create", "update", "get", or "list"
• teamId (required): Team ID to manage cycles for
• cycleId (optional, required for update and get actions): Cycle ID
• name (optional, required for create): Cycle name
• startDate (optional, required for create): Start date in ISO format (YYYY-MM-DD)
• endDate (optional, required for create): End date in ISO format (YYYY-MM-DD)
• description (optional): Cycle description

Team Management

Search and retrieve Linear teams with linear_search_teams:

• query (optional): Text to search in team names

Performance Features

The server includes several features that ensure reliable performance:

• In-memory caching for frequently accessed data
• Comprehensive error handling with automatic reconnection
• Batch processing for bulk operations
• Pagination support for large result sets
• Parallel processing for concurrent operations

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.