linear
A server that integrates Linear's project management system with the Model Context Protocol (MCP) to allow LLMs to interact with Linear.
claude mcp add --transport stdio jerhadf-linear-mcp-server npx -y linear-mcp-server \ --env LINEAR_API_KEY="your_linear_api_key_here"
How to use
The Linear MCP Server provides a Model Context Protocol interface to Linear's issue tracking system. It exposes tools that let you create, update, search, and comment on Linear issues directly through MCP-enabled clients. Core tools include linear_create_issue for creating issues, linear_update_issue for updating existing issues, linear_search_issues for flexible filtering and retrieval, linear_get_user_issues to fetch issues assigned to a user, and linear_add_comment to append comments to issues. The server relies on a Linear API key (set via LINEAR_API_KEY) to authenticate requests and access team and issue data. You can reference useful Linear resources via the provided URIs (linear-issue:///{issueId}, linear-team:///{teamId}/issues, etc.) to navigate to entries in the UI while composing prompts for your MCP-enabled assistant.
When interacting with the server, prompts can be crafted to target specific capabilities—for example, searching for high-priority issues, creating a new issue in a given team, or adding a comment to an existing issue. You can also combine multiple capabilities by invoking the relevant tools in sequence to achieve complex workflows, such as locating an issue, updating its status, and notifying the team through a comment.
How to install
Prerequisites:
- Node.js and npm installed on your machine
- A Linear API key for your team
Automatic installation (via Smithery):
- Run: npx @smithery/cli install linear-mcp-server --client claude
Manual installation:
- Obtain a Linear API key for your team: https://linear.app/YOUR-TEAM/settings/api
- Add the MCP server configuration to Claude Desktop (or your MCP client config) as follows:
{
"mcpServers": {
"linear": {
"command": "npx",
"args": [
"-y",
"linear-mcp-server"
],
"env": {
"LINEAR_API_KEY": "your_linear_api_key_here"
}
}
}
}
- Install dependencies and prepare the server:
npm install
- Set the Linear API key in your environment or in the provided config:
export LINEAR_API_KEY=your_linear_api_key_here
- Build and run the server (configured to use npx by default):
npm run build
# or for development with auto-rebuild: npm run watch
- If using Claude Desktop, ensure the config.json points to the same mcpServers.linear entry shown above.
Additional notes
Important: This MCP server is deprecated and no longer maintained. If possible, migrate to the official Linear remote MCP server for up-to-date features and support. When configuring environment variables, never hard-code secrets in code; use your platform’s secret management or environment variables. If you encounter issues with API access, double-check the LINEAR_API_KEY scope and permissions for the team. The provided command uses npx to run the server; you can adapt to other execution environments if needed, but ensure the LINEAR_API_KEY is accessible to the process. Refer to Linear's API docs for rate limits and authentication details.
Related MCP Servers
mcp-for-beginners
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.
mcp-arr
MCP server for *arr media management suite
boilerplate
TypeScript Model Context Protocol (MCP) server boilerplate providing IP lookup tools/resources. Includes CLI support and extensible structure for connecting AI systems (LLMs) to external data sources like ip-api.com. Ideal template for creating new MCP integrations via Node.js.
claude-code
MCP Server connects with claude code local command.
mcp-jest
Automated testing for Model Context Protocol servers. Ship MCP Servers with confidence.
miro
MCP server for controlling Miro whiteboards with AI assistants