About Linear MCP Server
Linear MCP Server lets AI assistants retrieve Linear data through MCP. Its current capability is fetching a user's tickets in the Todo state by user ID or email address.
Key features
- 01Fetch Todo tickets by user ID
- 02Fetch Todo tickets by email
- 03Return ticket ID, title, URL, and priority
Use cases
- 01Review a user's Todo tickets
- 02Find an owner's pending work by email
MCP support
The MCP server exposes a tool for retrieving a specified user's Todo tickets, identified by user ID or email.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMELinear MCP Server
A Model Context Protocol (MCP) server for interacting with Linear. This server allows AI assistants to fetch data from Linear through the MCP standard.
Current Features
- Get a user's todo tickets by user ID or email address
Installation
- Clone this repository
- Install dependencies:
npm install - Create a
.envfile at the root of the project (copy from.env.example):
Get your Linear API key from the Linear Developer ConsoleLINEAR_API_KEY=your_linear_api_key_here
Development
Run the development server (with hot reload):
npm run dev
Building for Production
Build the TypeScript code:
npm run build
Run the compiled code:
npm start
Using with MCP clients
This MCP server implements the standard MCP protocol and can be used with any MCP client. The server exposes the following tools:
Using with Claude Code
To use this MCP server with Claude Code, run the following command:
claude mcp add linear-mcp-server -- node dist/index.js
This registers the Linear MCP server with Claude Code, allowing you to access Linear tickets directly from your Claude conversations.
get-user-todo-tickets
Gets all tickets in the "Todo" state for a specified user.
Parameters:
userId(optional): The ID of the useremail(optional): The email of the user
Note: You must provide either userId or email.
Example response:
[
{
"id": "issue-id",
"identifier": "PROJ-123",
"title": "Fix login issue",
"url": "https://linear.app/...",
"priority": 1
},
...
]
Contributing
Contributions are welcome! Feel free to submit a pull request.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.