Linear

Provides an MCP bridge to Linear for creating, updating, and querying issues, comments, and teams with safe write modes.

go

11

GitHub Stars

go

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "geropl-linear-mcp-go": {
      "command": "./linear-mcp-go",
      "args": [
        "serve"
      ],
      "env": {
        "LINEAR_API_KEY": "YOUR_LINEAR_API_KEY"
      }
    }
  }
}

You run a Linear MCP Server to bridge Linear’s API with the Model Context Protocol, enabling you to create, fetch, and manage Linear data via MCP requests. This server runs locally as a Go binary and is designed to work with AI assistants and MCP clients to automate issue management, comments, teams, and more, while respecting Linear’s rate limits.

How to use

Set up your environment and start using the Linear MCP Server with an MCP client. Before you connect, ensure you have a valid Linear API key and the MCP server running on your machine. You will interact with the server through MCP requests to perform actions like creating issues, searching for issues, adding comments, and retrieving teams.

Start the server from your terminal. The server runs as a local process and communicates over standard input and output. Use the supplied command to launch it in read-only mode by default, or enable write access when needed.
Configure your MCP client to point to the running server. The client will send requests for actions such as creating issues, updating issues, and adding comments. If you enable write access, the client can modify Linear data according to the permissions you provide.
Provide your Linear API key to the server via the LINEAR_API_KEY environment variable. The server uses this key to authenticate with Linear’s API and perform actions on your behalf.

How to install

Prerequisites: Go 1.23 or higher and a valid Linear API key.

From Releases. Pre-built binaries are available for Linux, macOS, and Windows.

Download the appropriate binary for your platform from the release assets.
Make the binary executable. For Linux and macOS, run: chmod +x linear-mcp-go-*.
Run the binary to start the server according to your needs, for example: ./linear-mcp-go serve.

Automated installation. Retrieve the latest Linux binary, make it executable, and use the setup flow to configure for your AI assistants.

Download the Linux binary for the latest release, then: RELEASE=$(curl -s https://api.github.com/repos/geropl/linear-mcp-go/releases/latest) DOWNLOAD_URL=$(echo $RELEASE | jq -r '.assets[] | select(.name | contains("linux")) | .browser_download_url') curl -L -o ./linear-mcp-go $DOWNLOAD_URL chmod +x ./linear-mcp-go
Set up the MCP server for your AI assistants: ./linear-mcp-go setup --tool=cline.
Run the server with your desired permissions by including the write-access flag when needed: ./linear-mcp-go serve or ./linear-mcp-go serve --write-access.

Notes and security

The server operates with rate-limited API requests to respect Linear’s limits. Keep your Linear API key secure and only share credentials with trusted automation processes. When enabling write access, ensure you understand the implications for creating and updating Linear data.

For AI assistant integration, you can use the setup flow to auto-approve specific tools or enable read-only operation by default, then selectively enable write-enabled tools as you validate the workflow.

Available tools

linear_create_issue

Creates a new Linear issue with details like title, team, description, priority, status, and optional parent sub-issues and labels.

linear_update_issue

Updates properties of an existing Linear issue such as title, description, priority, and status.

linear_search_issues

Searches issues using criteria such as text query, team, status, assignee, labels, priority, and more.

linear_get_user_issues

Retrieves issues assigned to a specific user or the authenticated user.

linear_get_issue

Retrieves a single Linear issue by its ID.

linear_add_comment

Adds a comment to an issue and supports replying to existing comments via a thread identifier. URL-aware thread resolution is supported.

linear_reply_to_comment

Replies to an existing comment by automatically resolving the issue from the comment.

linear_get_issue_comments

Retrieves comments for an issue with pagination and thread navigation.

linear_update_issue_comment

Updates a specific comment on an issue.

linear_get_teams

Retrieves Linear teams with an optional name filter.