Linear MCP Server
Provides tools for interacting with the Linear API, enabling users to fetch, search, create, and update issues, add comments, and list teams, users, and workflow states within the Linear workspace.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Linear MCP Server Create a new high priority issue for the login bug in team ENG"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🚀 Linear-MCP-for-Gemini_CLI
A powerful, open-source Model Context Protocol (MCP) server specifically built to bridge Gemini CLI directly to your Linear workspace. Manage issues, teams, and workflows seamlessly through natural language, right from your terminal.
🌟 Features
🔍 Search & Discovery: Find issues across your entire workspace directly from Gemini CLI.
📝 Issue Management: Fetch, create, and update issues (status, priority, assignee, etc.) effortlessly.
💬 Collaboration: Add comments to issues without leaving your terminal.
🏢 Workspace Insights: List teams, users, and workflow states to provide full context to Gemini.
⚡ Real-time Integration: Built on the Model Context Protocol for low-latency, secure communication.
Related MCP server: Linear MCP Server
📋 Prerequisites
Before you begin, ensure you have the following installed:
Node.js: Version 18.0.0 or higher.
Gemini CLI: Installed and configured on your machine.
Linear Account: With access to generate an API key.
📖 Complete Gemini CLI Integration Guide
This server is written in TypeScript. Because Gemini CLI requires a standard JavaScript executable to run MCP servers, we first need to download and "build" the project.
Follow these 4 steps to get everything connected.
Step 1: Download & Build the Server
Clone the repository to your machine:
git clone https://github.com/tenx-studio/Linear-MCP.git cd linear-mcp-open-sourceInstall the required packages:
npm installCompile the code:
npm run build(Why do this? This command translates the TypeScript code into a
dist/index.jsfile, which is the exact file Gemini CLI will use to communicate with Linear).
Step 2: Get your Linear API Key
Navigate to Settings > API > Personal API keys in your Linear workspace.
Click New API key and give it a descriptive name (e.g., "Gemini CLI").
Copy the key (you will need it for the final step).
Step 3: Connect to Gemini CLI (The Only Setup You Need)
Now we tell Gemini CLI where to find the built server and securely provide it with your API key. You do this by editing the Gemini CLI settings file.
Locate your Settings File: Open your file explorer or terminal and find the
.geminifolder in your user's home directory:Windows:
%USERPROFILE%\.gemini\settings.json(e.g.,C:\Users\YourName\.gemini\settings.json)Mac/Linux:
~/.gemini/settings.json(Note: If the.geminifolder orsettings.jsonfile does not exist yet, simply create them).
Add the Configuration: Open
settings.jsonin any text editor (like VS Code, Notepad, or TextEdit) and paste the followingmcpblock. If your file already has content, just add the"mcp"section inside the main{}brackets:
{
"mcp": {
"servers": {
"linear": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/linear-mcp-open-source/dist/index.js"],
"env": {
"LINEAR_API_KEY": "lin_api_your_key_here"
}
}
}
}
}⚠️ Crucial Adjustments:
args: You MUST replace/ABSOLUTE/PATH/TO/...with the actual, full path on your computer where you cloned this repository. (e.g.,"D:/Projects/linear-mcp-open-source/dist/index.js").LINEAR_API_KEY: Replacelin_api_your_key_herewith the exact API key you copied in Step 2.
Step 4: Start Chatting!
Close and reopen your terminal to restart your Gemini CLI session. The integration is now active!
Try asking Gemini CLI things like:
"List my Linear teams." "Find the issue about the login bug." "Create a new high priority issue in the Engineering team to update the README."
🤖 Auto-Connection Magic (How it Works)
You might be wondering: "Do I need to run npm start every time I want to use this? Do I need to manually set up a server connection?"
No! You do not have to do anything extra.
Adding the configuration block in Step 3 is the only setup required. Here is exactly what happens under the hood:
Zero-Touch Startup: Because you added the configuration to your
settings.json, Gemini CLI natively acts as the host.Background Execution: Every time you start a new Gemini CLI chat, it automatically spins up this Linear MCP server in a hidden background process.
Secure Handshake: Gemini CLI reads the
"LINEAR_API_KEY"from your settings and securely injects it directly into the server.Clean Shutdown: When you close Gemini CLI, the background server is automatically terminated.
You just configure it once in your settings, and the Model Context Protocol handles the entire lifecycle for you automatically!
🤝 Contributing
Contributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
Fork the Project
Create your Feature Branch (
git checkout -b feature/AmazingFeature)Commit your Changes (
git commit -m 'Add some AmazingFeature')Push to the Branch (
git push origin feature/AmazingFeature)Open a Pull Request
📄 License
This project is licensed under the ISC License.
Built with ❤️ for the AI Developer Community.
Available Tools
8 toolslinear_add_commentC
Add a comment to an issue
Inputs: issueId (required), body (required).
linear_create_issueC
Create a new issue in a team
Inputs: teamId (required), title (required), description.
linear_get_issuesC
Get issues from a specific team
Inputs: teamKey, limit.
linear_get_teamsC
List all teams in the workspace
Inputs: limit.
linear_get_usersC
List all users in the workspace
Inputs: limit.
linear_get_workflow_statesC
Get workflow states for a specific team
Inputs: teamId (required).
linear_search_issuesC
Search for issues using a query
Inputs: query (required), limit.
linear_update_issueC
Update an existing issue
Inputs: issueId (required), title, description, stateId, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose targeting specific resources and actions in the Linear domain, such as creating issues, getting issues, adding comments, updating issues, searching issues, and retrieving teams, users, and workflow states. There is no ambiguity or overlap in functionality, making it easy for an agent to select the correct tool.
All tool names follow a consistent 'linear_verb_noun' pattern with snake_case, such as linear_create_issue, linear_get_issues, and linear_update_issue. This predictability enhances readability and usability for agents, with no deviations in naming conventions.
With 8 tools, the server is well-scoped for managing issues and related resources in Linear, covering core operations like CRUD for issues, commenting, searching, and retrieving teams, users, and states. Each tool earns its place without feeling excessive or insufficient for the domain.
The tool set provides strong coverage for issue management, including create, get, update, comment, and search, along with essential context tools for teams, users, and workflow states. A minor gap is the lack of delete operations for issues or other resources, but agents can work around this with updates or other methods.
Maintenance
Related MCP Connectors
Issues, projects, cycles, and roadmaps via the official Linear hosted MCP server.
Search, read and create Linear issues, projects, teams and cycles.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Linear MCP — wraps the Linear GraphQL API (OAuth)
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.418 npm346MIT
- AlicenseAqualityDmaintenanceA Model Context Protocol server that integrates with Linear, enabling AI assistants to create, update, search, and comment on issues for project management and issue tracking.549 PyPI6Apache 2.0
- FlicenseBqualityDmaintenanceA server that enables AI assistants to interact with Linear's project management tools through the Model Context Protocol, supporting features like searching, creating, and updating issues, adding comments, and retrieving user profiles and team information.91-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server implementation that enables AI assistants to interact with Linear project management systems, allowing them to create, retrieve, and modify data related to issues, projects, teams, and users.21 npm3MIT