Sandbox
@jerhadf/linear-mcp-server

MCP server for Linear issue tracking

This project exposes Linear through the Model Context Protocol so an agent can work with issues, comments, teams, and user context. It ships tools for creating, updating, searching, and commenting on issues, plus resources for issue and team views.

348 stars56 forksJavaScriptUpdated 1y ago
Who it's for

Builders who want their agent to work with Linear issues and project data.

What it delivers

You can manage Linear work from your agent instead of switching between chat and the Linear app.

What it does

Create issues

`linear_create_issue` makes a new Linear issue with title, team, description, priority, and status.

Update issues

`linear_update_issue` changes an existing issue’s title, description, priority, or status.

Search issues

`linear_search_issues` filters by query, team, status, assignee, labels, priority, and result limit.

Get assigned issues

`linear_get_user_issues` returns issues for a user or the signed-in account, with archived issue support.

Add comments

`linear_add_comment` posts markdown comments to an issue, with optional custom author name and avatar.

Expose Linear resources

Resources include issue, team, user, organization, and viewer URIs for reading Linear context.

How to get it

  1. 1To install the Linear MCP server for Claude Desktop automatically via Smithery
    npx @smithery/cli install linear-mcp-server --client claude

README

Linear MCP Server

npm version smithery badge

IMPORTANT NOTE: This MCP Server is now deprecated and is no longer being maintained. I recommend you use the official Linear remote MCP server here: https://linear.app/changelog/2025-05-01-mcp (https://mcp.linear.app/sse)

A Model Context Protocol server for the Linear API.

This server provides integration with Linear's issue tracking system through MCP, allowing LLMs to interact with Linear issues.

Installation

Automatic Installation

To install the Linear MCP server for Claude Desktop automatically via Smithery:

npx @smithery/cli install linear-mcp-server --client claude

Manual Installation

  1. Create or get a Linear API key for your team: https://linear.app/YOUR-TEAM/settings/api

  2. Add server config to Claude Desktop:

    • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "linear": {
      "command": "npx",
      "args": [
        "-y",
        "linear-mcp-server"
      ],
      "env": {
        "LINEAR_API_KEY": "your_linear_api_key_here"
      }
    }
  }
}

Components

Tools

  1. linear_create_issue: Create a new Linear issues

    • Required inputs:
      • title (string): Issue title
      • teamId (string): Team ID to create issue in
    • Optional inputs:
      • description (string): Issue description (markdown supported)
      • priority (number, 0-4): Priority level (1=urgent, 4=low)
      • status (string): Initial status name
  2. linear_update_issue: Update existing issues

    • Required inputs:
      • id (string): Issue ID to update
    • Optional inputs:
      • title (string): New title
      • description (string): New description
      • priority (number, 0-4): New priority
      • status (string): New status name
  3. linear_search_issues: Search issues with flexible filtering

    • Optional inputs:
      • query (string): Text to search in title/description
      • teamId (string): Filter by team
      • status (string): Filter by status
      • assigneeId (string): Filter by assignee
      • labels (string[]): Filter by labels
      • priority (number): Filter by priority
      • limit (number, default: 10): Max results
  4. linear_get_user_issues: Get issues assigned to a user

    • Optional inputs:
      • userId (string): User ID (omit for authenticated user)
      • includeArchived (boolean): Include archived issues
      • limit (number, default: 50): Max results
  5. linear_add_comment: Add comments to issues

    • Required inputs:
      • issueId (string): Issue ID to comment on
      • body (string): Comment text (markdown supported)
    • Optional inputs:
      • createAsUser (string): Custom username
      • displayIconUrl (string): Custom avatar URL

Resources

  • linear-issue:///{issueId} - View individual issue details
  • linear-team:///{teamId}/issues - View team issues
  • linear-user:///{userId}/assigned - View user's assigned issues
  • linear-organization: - View organization info
  • linear-viewer: - View current user context

Usage examples

Some example prompts you can use with Claude Desktop to interact with Linear:

  1. "Show me all my high-priority issues" → execute the search_issues tool and/or linear-user:///{userId}/assigned to find issues assigned to you with priority 1

  2. "Based on what I've told you about this bug already, make a bug report for the authentication system" → use create_issue to create a new high-priority issue with appropriate details and status tracking

  3. "Find all in progress frontend tasks" → use search_issues to locate frontend-related issues with in progress task

  4. "Give me a summary of recent updates on the issues for mobile app development" → use search_issues to identify the relevant issue(s), then linear-issue:///{issueId} fetch the issue details and show recent activity and comments

  5. "What's the current workload for the mobile team?" → combine linear-team:///{teamId}/issues and search_issues to analyze issue distribution and priorities across the mobile team

Development

  1. Install dependencies:
npm install
  1. Configure Linear API key in .env:
LINEAR_API_KEY=your_api_key_here
  1. Build the server:
npm run build

For development with auto-rebuild:

npm run watch

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

Files in the repo

Repository payload7 top-level entries
  • .gitignore
  • index.ts
  • LICENSE
  • package-lock.json
  • package.json
  • README.md
  • tsconfig.json

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k