About Linear MCP Server
Linear MCP Server connects AI assistants to Linear project management data and operations. It covers a broad range of Linear entities and provides resources, management tools, search, and prompt templates.
Key features
- 01Access issues, projects, teams, and more
- 02Create and update issues and projects
- 03Manage initiatives and project links
- 04Search Linear entities and issues
- 05Use issue and project prompt templates
Use cases
- 01Look up Linear issues, teams, or roadmaps
- 02Create or update issues from an assistant
- 03Organize projects under initiatives
- 04Draft bug reports and project updates
MCP support
Exposes Linear resources, tools, and prompt templates to MCP clients. It supports stdio and HTTP with SSE transports.
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 Linear, providing AI assistants with access to Linear's project management capabilities.
Features
- Resources: Access issues, projects, teams, users, roadmaps, documents, initiatives, and more
- Tools: Create and update issues, manage projects, search, link projects to initiatives
- Prompts: Templates for issue creation, bug reports, feature requests, and more
Setup
Prerequisites
- Node.js 18 or later
- A Linear API key
Installation
-
Clone the repository:
git clone https://github.com/yourusername/linear-mcp.git cd linear-mcp -
Install dependencies:
npm install -
Create a
.envfile with your Linear API key:LINEAR_API_KEY=your_linear_api_key_here -
Build the project:
npm run build
Usage
Command-line (stdio)
To run the server with stdio transport (for use with CLI tools that support MCP):
npm start
Or:
node dist/index.js stdio
HTTP Server (for remote connections)
To run the server as an HTTP service with Server-Sent Events (SSE):
node dist/index.js http
This will start an HTTP server on port 3000 (configurable via PORT environment variable).
Development Mode
To run in development mode with automatic reloading:
npm run dev
Claude Desktop Integration
To use this server with Claude Desktop:
-
Build the project:
npm run build -
In Claude Desktop, go to Settings → Advanced → MCP Configuration.
-
Add the following configuration (adjust paths to match your installation):
{ "mcpServers": { "linear": { "command": "node", "args": [ "/path/to/linear-mcp/dist/index.js" ], "env": { "LINEAR_API_KEY": "your_linear_api_key_here" } } } } -
Save the configuration and restart Claude Desktop.
Alternatively, you can copy the provided claude-desktop-config.json file and modify the paths to match your installation.
Resources
The server provides access to all major Linear entities as resources:
Core Resources
- Issues:
linear://issuesandlinear://issues/{id} - Teams:
linear://teamsandlinear://teams/{id} - Projects:
linear://projectsandlinear://projects/{id} - Users:
linear://usersandlinear://users/{id} - Initiatives:
linear://initiativesandlinear://initiatives/{id}
Additional Resources
- Roadmaps:
linear://roadmapsandlinear://roadmaps/{id} - Milestones:
linear://milestonesandlinear://milestones/{id} - Documents:
linear://documentsandlinear://documents/{id} - Integrations:
linear://integrationsandlinear://integrations/{id} - Organization:
linear://organization
Specialized Resources
linear://teams/{teamId}/issues- Issues for a specific teamlinear://users/{userId}/issues- Issues assigned to a specific userlinear://projects/{projectId}/issues- Issues in a specific projectlinear://teams/{teamId}/states- Workflow states for a teamlinear://teams/{teamId}/labels- Labels for a teamlinear://teams/{teamId}/cycles- Cycles for a teamlinear://teams/{teamId}/members- Members of a teamlinear://teams/{teamId}/documents- Documents for a teamlinear://projects/{projectId}/documents- Documents for a projectlinear://projects/{projectId}/initiative- Initiative associated with a projectlinear://initiatives/{initiativeId}/projects- Projects associated with an initiativelinear://milestones/{milestoneId}/projects- Projects for a milestonelinear://organization/subscription- Organization subscription detailslinear://organization/auth-services- Organization authentication serviceslinear://integration-services- Available integration services
Tools
The server provides tools for:
-
Issue Management
- Creating new issues
- Updating existing issues
- Adding comments to issues
-
Project Management
- Creating new projects
- Updating existing projects
- Adding issues to projects
-
Initiative Management
- Creating initiatives
- Linking projects to initiatives
- Unlinking projects from initiatives
-
Search Capabilities
- Comprehensive search across Linear entities
- Finding issues with specific criteria
Prompts
The server provides prompt templates for:
-
Issue Related
- Creating new issues
- Creating bug reports
- Creating feature requests
-
Project Related
- Creating new projects
- Planning projects with issues
- Creating project status updates
Testing
Test with the MCP Inspector:
npx @modelcontextprotocol/inspector stdio -- npm start
Or, if running in HTTP mode, open the MCP Inspector in your browser and connect to your server's URL.
Environment Variables
LINEAR_API_KEY(required): Your Linear API keySERVER_PORT(optional): Port for HTTP server (default: 3000)LOG_LEVEL(optional): Logging level (default: info)
License
MIT
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.