This MCP server enables AI models to interact with Linear for issue tracking and project management through the Model Context Protocol. It provides tools for creating issues, searching, managing sprints, and more.
.env
file in the project root with your Linear API key:LINEAR_API_KEY=your_api_key_here
npm install
# Development mode with auto-reload
npm run dev
# Production mode
npm start
The linear_create_issue
tool allows you to create new Linear issues with various parameters:
// Required parameters
{
"title": "Fix login button styling",
"teamId": "TEAM_ID_HERE"
}
// With optional parameters
{
"title": "Fix login button styling",
"teamId": "TEAM_ID_HERE",
"description": "The button is misaligned on mobile devices",
"priority": 2,
"status": "In Progress"
}
Use linear_search_issues
to find issues with flexible filtering:
// Simple search
{
"query": "login button"
}
// Advanced filtering
{
"teamId": "TEAM_ID_HERE",
"status": "In Progress",
"assigneeId": "USER_ID_HERE",
"priority": 2,
"limit": 20,
"sortBy": "updated",
"sortDirection": "desc"
}
Get all issues in the current sprint with linear_sprint_issues
:
{
"teamId": "TEAM_ID_HERE"
}
Filter sprint issues by status with linear_filter_sprint_issues
:
{
"teamId": "TEAM_ID_HERE",
"status": "Pending Prod Release"
}
Search and retrieve teams with linear_search_teams
:
{
"query": "engineering"
}
Get comprehensive information about a specific issue:
{
"issueId": "DATA-1284"
}
Update multiple issues at once:
{
"issueIds": ["ENG-123", "DATA-456"],
"targetStatus": "In Progress"
}
Manage Linear cycles (sprints) with the linear_manage_cycle
tool:
// Create a new cycle
{
"action": "create",
"teamId": "TEAM_ID_HERE",
"name": "Sprint 42",
"startDate": "2023-06-01",
"endDate": "2023-06-14",
"description": "Focus on UI improvements"
}
// Get information about a cycle
{
"action": "get",
"teamId": "TEAM_ID_HERE",
"cycleId": "CYCLE_ID_HERE"
}
// List all cycles
{
"action": "list",
"teamId": "TEAM_ID_HERE"
}
You can deploy this server on Smithery.ai:
# Build the Docker image
docker build -t linear-mcp-server .
# Run the container with your Linear API key
docker run -e LINEAR_API_KEY=your_api_key_here linear-mcp-server
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "linear" '{"command":"npx","args":["-y","@skspade/mcp-linear-server"]}'
See the official Claude Code MCP documentation for more details.
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.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"linear": {
"command": "npx",
"args": [
"-y",
"@skspade/mcp-linear-server"
]
}
}
}
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.
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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"linear": {
"command": "npx",
"args": [
"-y",
"@skspade/mcp-linear-server"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect