Implementation of an MCP server for Linear integration
What is scoutos mcp linear
Linear MCP Server
A Node.js 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.
Key Features
- Standard MCP protocol implementation for Linear using the official MCP SDK
- Support for searching issues, reading details, updating, and commenting
Getting Started
Prerequisites
- Node.js (v18 or later)
- Linear API key
Installation
- Clone the repository
- Install dependencies
npm install
- Create a
.env
file in the root directory with your Linear API key
LINEAR_API_KEY=your_linear_api_key_here
Running the Server
Start the server:
npm start
For development with file watching:
just dev
For development with debug logging:
just debug
Or set environment variables manually:
LOG_LEVEL=DEBUG NODE_ENV=development node src/index.js
Logs will be written to the logs/mcp-linear.log
file to avoid interfering with the STDIO transport.
Using with MCP Inspector
The server runs in stdio mode, which means you can connect to it with the MCP Inspector.
- Start the server in one terminal:
npm start
-
Visit the web-based inspector at: https://inspector.modelcontextprotocol.ai
-
Select "stdio" as the transport type
-
Enter the following command:
node /path/to/mcp-linear/src/index.js
- Click "Connect" to connect to your running server
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": "node /path/to/mcp-linear/src/index.js",
"env": {
"LINEAR_API_KEY": "your_linear_api_key_here"
}
}
]
}
}
Usage with Cursor
For Cursor, add the following to your settings:
{
"ai.mcp.servers": [
{
"name": "Linear",
"command": "node /path/to/mcp-linear/src/index.js",
"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
Project Structure
/
โโโ src/ # Source code
โ โโโ effects/ # Effects implementation
โ โ โโโ linear/ # Linear API effects
โ โ โ โโโ types/ # Linear type definitions
โ โ โโโ logging/ # Logging effects for safe logging with STDIO
โ โโโ tools/ # MCP tools implementation
โ โ โโโ types/ # Tool type definitions
โ โ โโโ utils/ # Tool utility functions
โ โโโ utils/ # Utility modules
โ โ โโโ config/ # Configuration utilities
โ โโโ index.js # Main entry point
โโโ docs/ # Documentation
โ โโโ llm_context/ # Documentation for LLMs
โโโ logs/ # Log files (created at runtime)
โโโ package.json # Project configuration
Available Tools
The MCP server exposes the following tools:
list_issues
- List Linear issues (also called tickets) with various filtering options (assignee, status, etc.)get_issue
- Get detailed information about a specific Linear issue by IDlist_members
- List Linear team members with optional filtering by namelist_projects
- List Linear projects with optional filtering by team, name, and archive statusget_project
- Get detailed information about a specific Linear project including issues, members and morelist_teams
- List Linear teams with details about their members, projects, and issuesadd_comment
- Add a comment to a specific Linear issuecreate_issue
- Create a new issue in Linear with customizable title, description, priority, and assignee
For backward compatibility, the following tool aliases are also available:
list_tickets
- Alias forlist_issues
get_ticket
- Alias forget_issue
Troubleshooting
If you're having issues with the Linear MCP server:
-
Check your Linear API key: Make sure you've set a valid Linear API key in your .env file or environment variables. Linear API keys should start with "linapi".
-
Enable debug logging:
a. When starting the MCP server:
just debug # or LOG_LEVEL=DEBUG NODE_ENV=development node src/index.js
b. In your client configuration (Claude Desktop, Cursor, etc.):
"env": { "LINEAR_API_KEY": "your_linear_api_key_here", "LOG_LEVEL": "DEBUG" }
c. When calling tools directly, add the debug parameter:
{ "debug": true }
-
Check log files: Examine logs in the
logs/mcp-linear.log
file for detailed error information. -
Verify Linear API access: Make sure your Linear API key has appropriate permissions and that you can access the Linear API directly.
Architecture
The application follows an effects-based architecture:
-
Effects: Side-effecting operations are isolated in the
effects
directory:linear
: Provides access to Linear API using the official Linear SDKlogging
: Safe logging that doesn't interfere with STDIO transport
-
Tools: MCP tool implementations that use effects for side-effects:
- Each tool follows a consistent pattern with input validation using Zod
- Tools are exposed through the MCP protocol via the server
- Each tool can access the Linear client through the linear effect
-
Utils: Utility modules for configuration and common functionality
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Leave a Comment
Frequently Asked Questions
What is MCP?
MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.
What are MCP Servers?
MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.
How do MCP Servers work?
MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.
Are MCP Servers secure?
Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.
Related MCP Servers
chrisdoc hevy mcp
sylphlab pdf reader mcp
An MCP server built with Node.js/TypeScript that allows AI agents to securely read PDF files (local or URL) and extract text, metadata, or page counts. Uses pdf-parse.
aashari mcp server atlassian bitbucket
Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.
aashari mcp server atlassian confluence
Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.
prisma prisma
Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB
Zzzccs123 mcp sentry
mcp sentry for typescript sdk
zhuzhoulin dify mcp server
zhongmingyuan mcp my mac
zhixiaoqiang desktop image manager mcp
MCP ๆๅกๅจ๏ผ็จไบ็ฎก็ๆก้ขๅพ็ใๆฅ็่ฏฆๆ ใๅ็ผฉใ็งปๅจ็ญ๏ผๅฎๅ จ่ฎฉTraeๅฎ็ฐ๏ผ
zhixiaoqiang antd components mcp
An MCP service for Ant Design components query | ไธไธชๅๅฐ Ant Design ็ปไปถไปฃ็ ็ๆๅนป่ง็ MCP ๆๅก๏ผๅ ๅซ็ณป็ปๆ็คบ่ฏใ็ปไปถๆๆกฃใAPI ๆๆกฃใไปฃ็ ็คบไพๅๆดๆฐๆฅๅฟๆฅ่ฏข
Submit Your MCP Server
Share your MCP server with the community
Submit Now