
Linear
dvcrn
README
Linear MCP Server
An MCP server for interacting with Linear's API. This server provides a set of tools for managing Linear issues, projects, and teams through Cline.
Setup Guide
1. Get Linear API Token
- Go to Linear: Settings > API > OAuth application > "Cline MCP"
- Under "Developer Token", click "Create & copy token"
- Select "Application" and copy the generated token
2. Configure Cline MCP
-
Open your Cline MCP settings file:
- macOS:
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Windows:
%APPDATA%/Code/User/GlobalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Linux:
~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- macOS:
-
Add the Linear MCP server configuration:
{ "mcpServers": { "linear": { "command": "npx", "args": ["mcp-server-linear"], "env": { "LINEAR_ACCESS_TOKEN": "your_linear_api_token_here" }, "disabled": false, "autoApprove": [] } } }
That's it! The server will be automatically downloaded and run through npx when needed.
If you use Cline/Roo, you can also simply tell it install the MCP from https://github.com/dvcrn/mcp-server-linear
and it'll do the rest.
Note: Replace your_linear_api_token_here
with the API token you generated in step 1.
Available Actions
The server currently supports the following operations:
Issue Management
- ✅ Create issues with full field support (title, description, team, project, parent/child relationships, etc.)
- ✅ Update existing issues (priority, description, etc.)
- ✅ Delete issues (single or bulk deletion)
- ✅ Search issues with filtering and by identifier
- ✅ Associate issues with projects
- ✅ Create parent/child issue relationships
- ✅ Comment management (create, update, delete comments)
- ✅ Comment resolution handling (resolve/unresolve comments)
- ✅ Create customer needs from attachments
Project Management
- ✅ Create projects with associated issues
- ✅ Get project information
- ✅ List all projects with optional filtering
- ✅ Associate issues with projects
- ✅ Project milestone management (create, update, delete)
- ✅ List and filter project milestones
Team Management
- ✅ Get team information (with states and workflow details)
- ✅ Access team states and labels
Authentication
- ✅ Personal Access Token (PAT) authentication
- ✅ Secure token storage
Batch Operations
- ✅ Bulk issue creation
- ✅ Bulk issue deletion
Bulk Updates (In Testing)
- 🚧 Bulk issue updates (parallel processing implemented, needs testing)
Features in Development
The following features are currently being worked on:
Issue Management
- 🚧 Complex search filters
- 🚧 Pagination support for large result sets
Metadata Operations
- 🚧 Label management (create/update/assign)
Project Management
- ✅ Project milestone management
- 🚧 Project template support
- 🚧 Advanced project operations
Authentication
- 🚧 OAuth flow with automatic token refresh
Performance & Security
- 🚧 Rate limiting
- 🚧 Detailed logging
- 🚧 Load testing and optimization
Parent/Child Issue Relationships
The server supports creating and managing hierarchical relationships between issues:
Creating Sub-issues
You can create sub-issues by specifying a parent issue's UUID when creating a new issue:
{
"title": "Sub-task Implementation",
"description": "Implement this specific part of the parent task",
"teamId": "team_uuid",
"parentId": "parent_issue_uuid"
}
Note: The parentId must be the UUID of the parent issue, not the issue identifier (e.g., use the UUID, not "ENG-123").
Using Multiple Linear Workspaces
You can connect to multiple Linear workspaces by adding the Linear MCP server multiple times with different TOOL_PREFIX
values. This allows you to work with separate Linear workspaces within the same Cline environment.
Configuration Example
{
"mcpServers": {
"company1-linear": {
"command": "npx",
"args": ["mcp-server-linear"],
"env": {
"LINEAR_ACCESS_TOKEN": "your_company1_linear_token_here",
"TOOL_PREFIX": "company1"
},
"disabled": false,
"autoApprove": []
},
"company2-linear": {
"command": "npx",
"args": ["mcp-server-linear"],
"env": {
"LINEAR_ACCESS_TOKEN": "your_company2_linear_token_here",
"TOOL_PREFIX": "company2"
},
"disabled": false,
"autoApprove": []
},
"company3-linear": {
"command": "npx",
"args": ["mcp-server-linear"],
"env": {
"LINEAR_ACCESS_TOKEN": "your_company3_linear_token_here",
"TOOL_PREFIX": "company3"
},
"disabled": false,
"autoApprove": []
}
}
}
How It Works
When you set a TOOL_PREFIX
value:
- All tool names are prefixed with it (e.g.,
company1_linear_create_issue
) - Tool descriptions include the prefix (e.g., "For 'company1' Linear workspace: Create a new issue")
This makes it clear which workspace each tool is operating on and prevents conflicts between different Linear instances.
Contributing
If you want to contribute to the development of this MCP server, follow these steps:
- Clone the repository
- Install dependencies:
npm install
- Copy
.env.example
to.env
:cp .env.example .env
- Add your Linear API token to
.env
:LINEAR_ACCESS_TOKEN=your_personal_access_token
Development
# Install dependencies
npm install
# Run tests
npm test
# Build and run the server locally
npm run build
npm start
# Or use development mode with auto-reload
npm run dev
Integration Testing
Integration tests verify that authentication and API calls work correctly:
- Set up authentication in
.env
(PAT recommended for testing) - Run integration tests:
npm run test:integration
For OAuth testing:
- Configure OAuth credentials in
.env
:LINEAR_CLIENT_ID=your_oauth_client_id LINEAR_CLIENT_SECRET=your_oauth_client_secret LINEAR_REDIRECT_URI=http://localhost:3000/callback
- Remove
.skip
from OAuth tests insrc/__tests__/auth.integration.test.ts
- Run integration tests
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.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A 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.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.