linear-mcp-server
MCP server for integrating Linear with Claude Code and other MCP clients. Enables issue management, project planning, and status tracking through a set of tools.
README
Linear MCP Server
MCP (Model Context Protocol) server for integrating Linear with Claude Code and other MCP clients.
Features
- Issue Management: Create, update, and query Linear issues
- Project Planning: Create projects and break them down into milestones
- Status Tracking: Update issue status through workflow states
- Progress Updates: Add comments and progress notes to issues
- Team Context: Query team information and workflow states
Installation
This project uses uv for dependency management.
# Install dependencies
uv sync
# Or with pip
pip install -e .
Configuration
-
Get your Linear API key:
- Go to Linear Settings > Account > Security & Access
- Create a new Personal API key
- Choose appropriate permissions (Read, Write, Create issues, Create comments)
-
Create
.envfile:cp .env.example .env # Edit .env and add your LINEAR_API_KEY
Usage with Claude Code
Add to your Claude Code configuration (~/.claude/config.json or project .claude/mcp-servers.json):
{
"mcpServers": {
"linear": {
"command": "uv",
"args": ["run", "linear-mcp-server"],
"cwd": "/Users/devonshurick/dev/personal/linear-mcp-server",
"env": {
"LINEAR_API_KEY": "lin_api_xxxxxxxxxxxx"
}
}
}
}
Or use environment variables:
{
"mcpServers": {
"linear": {
"command": "uv",
"args": ["run", "linear-mcp-server"],
"cwd": "/Users/devonshurick/dev/personal/linear-mcp-server"
}
}
}
Then set LINEAR_API_KEY in your .env file.
Available Tools
Issue Management
-
linear_create_issue- Create a new issue- Parameters:
title,description,team_id, optional:project_id,state_id,priority,assignee_id
- Parameters:
-
linear_update_issue- Update an existing issue- Parameters:
issue_id, optional:state_id,title,description,priority
- Parameters:
-
linear_list_issues- List issues for a team- Parameters:
team_id, optional:status_filter,assignee_id,limit
- Parameters:
-
linear_add_comment- Add a comment to an issue- Parameters:
issue_id,body
- Parameters:
Team & Workflow
-
linear_get_teams- List available teams -
linear_get_workflow_states- Get workflow states for a team- Parameters:
team_id
- Parameters:
Projects (Coming Soon)
linear_create_project- Create a new project with milestoneslinear_list_projects- List projects
Development
# Install with dev dependencies
uv sync --extra dev
# Run tests
uv run pytest
# Format code
uv run black .
# Lint
uv run ruff check .
Architecture
src/linear_mcp/
├── __init__.py
├── server.py # MCP server implementation
├── linear_client.py # Linear GraphQL API client
└── tools.py # Tool definitions for MCP
Use Cases
-
Task Execution with Progress Tracking
- Claude receives task → Creates Linear issue → Works on task → Updates issue with progress → Marks done
-
Project Planning
- User describes goal → Claude creates project → Breaks into milestones → Creates task issues → Links dependencies
-
Dynamic Prioritization
- Claude reviews backlog → Analyzes priorities → Proposes changes → Updates issues after approval
Linear API Reference
- Linear GraphQL API
- API Schema
- Rate Limits: 1,500 requests/hour per API key
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。