
Linear MCP Server
A Deno implementation that enables AI models to interact with Linear issue tracking functionality, supporting searching issues, reading details, updating, and commenting.
README
Linear MCP Server
A Deno 2.0 implementation of an MCP server for Linear integration.
About
This MCP (Model Context Protocol) server provides a standardized interface for AI models to interact with Linear issue tracking functionality. It follows the Actions and Effects architecture pattern for clear separation of concerns and testability.
Key Features
- Standard MCP protocol implementation for Linear
- Support for searching issues, reading details, updating, and commenting
- Clean architecture following functional programming principles
- Runs standalone without requiring Deno installation
Getting Started
Quick Start (No Installation Required)
Use the server directly without installation:
npx @scoutos/mcp-linear
Installation Options
Option 1: Using npm (Node.js)
# Install globally
npm install -g @scoutos/mcp-linear
# Run the server
mcp-linear
Option 2: Using Deno
If you have Deno installed:
# Run directly without installation
deno run --allow-env --allow-stdio https://deno.land/x/mcp_linear/main.ts
# Or install and run
deno install --allow-env --allow-stdio -n mcp-linear https://deno.land/x/mcp_linear/main.ts
mcp-linear
Usage with Claude Desktop
Add the following to your Claude Desktop configuration file (typically at ~/.config/Claude Desktop/claude_desktop_config.json
):
{
"mcp": {
"servers": [
{
"name": "Linear",
"command": "npx @scoutos/mcp-linear",
"env": {
"LINEAR_API_KEY": "your_linear_api_key_here"
}
}
]
}
}
Alternatively, you can use Docker:
{
"mcp": {
"servers": [
{
"name": "Linear",
"command": "docker run --rm -e LINEAR_API_KEY=your_linear_api_key_here scoutos/mcp-linear:latest"
}
]
}
}
Usage with Cursor
For Cursor, add the following to your settings:
{
"ai.mcp.servers": [
{
"name": "Linear",
"command": "npx @scoutos/mcp-linear",
"env": {
"LINEAR_API_KEY": "your_linear_api_key_here"
}
}
]
}
Testing Your Integration
To verify your setup:
- Configure the MCP server in your Claude Desktop or Cursor settings
- Restart your application
- Ask: "Search for Linear issues containing 'bug'"
- The assistant should detect and use the Linear MCP server to retrieve results
Development
This project uses Deno 2.0 and just for development workflow.
Prerequisites
First-time Setup
After cloning the repository, run:
just post-clone
This will set up the required git hooks to ensure consistent code quality.
Available Commands
# List all available commands
just
# Run the development server with file watching
just dev
# Start the server
deno task start
# Format code
just fmt
# Lint code
just lint
# Format and lint all files
just check
# Run tests
just test
# or
deno task test
# Check types
just check-types
# Set up git hooks (runs automatically from post-clone)
just setup-hooks
Developer Experience
This project includes:
- Pre-commit hooks to automatically format and lint staged files
- Deno's built-in formatter and linter
- Type checking through Deno
Building for Distribution
Building the npm Package
To build the package for npm distribution:
# Create a standalone executable
deno compile --allow-net --allow-env --output dist/mcp-linear main.ts
# Package for npm distribution
# This requires additional configuration in a package.json file
The binary will be available in the dist
directory and can be published to npm.
Publishing to Deno Land
To make the package available via deno.land/x
:
# Ensure all tests pass
just test
# Tag a new version
git tag v0.1.0
git push --tags
Then submit the module to deno.land/x
following their contribution guidelines.
Project Structure
/
├── effects/ # Core effect definitions and implementations
│ ├── http/ # HTTP effects for API communication
│ ├── storage/ # Storage effects for data persistence
│ └── logging/ # Logging effects for observability
├── types/ # Type definitions
├── token-sources/ # Token source implementations
├── actions/ # Business logic actions
├── mcp/ # MCP server implementation
│ ├── server.ts # Core server implementation
│ └── server.test.ts # Server tests
├── main.ts # Application entry point
└── main.test.ts # Main application tests
API Endpoints
The MCP server exposes the following endpoints:
GET /mcp
- Server informationGET /mcp/tools
- List available toolsPOST /mcp/tools/linear-search
- Search Linear issuesGET /mcp/tools/linear-issue/{id}
- Get issue detailsPUT /mcp/tools/linear-issue/{id}
- Update an issuePOST /mcp/tools/linear-issue/{id}/comment
- Add a comment to an issue
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.