Nav2 MCP Server
Enables control and monitoring of Nav2 navigation operations, including navigation, waypoints, costmap management, and lifecycle control, through the MCP protocol.
README
Nav2 MCP Server
An MCP (Model Context Protocol) server that provides tools and resources to control and monitor Nav2 navigation operations, allowing seamless integration with Nav2-enabled robots through the MCP protocol.

Features
- Navigation control: Navigate to specific poses, follow waypoint sequences, and execute precise robot movements
- Real-time status: Monitor navigation progress, robot pose, and system status with comprehensive feedback
- Costmap management: Clear stale obstacle data and manage navigation costmaps for optimal path planning
- Lifecycle management: Control Nav2 system startup and shutdown for complete system control
- ROS 2 integration: Full compatibility with Nav2 navigation stack and ROS 2 ecosystem
- Async operations: Non-blocking navigation commands with progress monitoring and cancellation support
Tools
| Tool | Description | Parameters |
|---|---|---|
| navigate_to_pose | Navigate the robot to a specific pose (position and orientation) in the map frame | x: float, y: float, yaw: float |
| follow_waypoints | Navigate the robot through a sequence of waypoints in order | waypoints: str (JSON array) |
| spin_robot | Rotate the robot in place by a specified angle | angle: float |
| backup_robot | Move the robot backward by a specified distance | distance: float, speed: float |
| dock_robot | Dock the robot to a charging station or dock | x: float, y: float, yaw: float, dock_id: str, dock_type: str, nav_to_dock: bool |
| undock_robot | Undock the robot from a charging station or dock | dock_type: str |
| clear_costmaps | Clear robot navigation costmaps to remove stale obstacle data | costmap_type: str |
| get_robot_pose | Get the current position and orientation of the robot | — |
| cancel_navigation | Cancel the currently active navigation task | — |
| nav2_lifecycle | Control Nav2 lifecycle (startup or shutdown) | action: str |
| get_path | Compute a navigation path between two poses | start_x: float, start_y: float, start_yaw: float, goal_x: float, goal_y: float, goal_yaw: float, planner_id: str |
| get_path_from_robot | Compute a navigation path from the robot's current pose to a goal pose | goal_x: float, goal_y: float, goal_yaw: float, planner_id: str |
Environment Variables
| Variable | Default | Description |
|---|---|---|
ROS_DOMAIN_ID |
— | ROS 2 domain ID for network isolation (recommended to set) |
ROS_LOCALHOST_ONLY |
— | Set to '1' to restrict ROS 2 communication to localhost only |
Configuration
Environment Variables
| Variable | Default | Description |
|---|---|---|
TRANSPORT_MODE |
stdio |
Transport mode: stdio (local integration) or http (network) |
HTTP_HOST |
0.0.0.0 |
HTTP host binding (only used when TRANSPORT_MODE=http) |
HTTP_PORT |
3001 |
HTTP port (only used when TRANSPORT_MODE=http) |
LOG_LEVEL |
INFO |
Logging level: DEBUG, INFO, WARNING, ERROR, CRITICAL |
ROS_DOMAIN_ID |
— | ROS 2 domain ID for network isolation (recommended) |
ROS_LOCALHOST_ONLY |
— | Set to '1' to restrict ROS 2 communication to localhost only |
Setup
- Copy the environment configuration template:
cp .env.example .env
- Edit
.envto customize settings:
# Transport mode: 'stdio' for local, 'http' for containerized/network
TRANSPORT_MODE=stdio
# HTTP settings (only needed if using http transport)
HTTP_HOST=0.0.0.0
HTTP_PORT=3001
# Logging
LOG_LEVEL=INFO
Installation
Dependencies
- Robot Operating System (ROS) 2: Middleware for robotics (Jazzy)
- fastmcp: MCP server framework
- python: Python programming language
- uv: Python package manager (optional)
Install with uv
Clone the repository and install with uv:
git clone https://github.com/ajtudela/nav2_mcp_server.git
cd nav2_mcp_server
# Set up ROS 2 environment variables if needed
export ROS_DOMAIN_ID=0
uv sync
Or install directly from the repository:
uv add git+https://github.com/ajtudela/nav2_mcp_server.git
Docker
Build the image
Build the image:
docker build -t nav2-mcp-server:latest .
Pull the image
Pull the latest image from the Docker registry:
docker pull ghcr.io/ajtudela/nav2_mcp_server:latest
Usage
Running with uv
uv run nav2_mcp_server
Configuration example for Claude Desktop/Cursor/VSCode
Add this configuration to your application's settings (mcp.json):
Using uv (stdio transport)
{
"nav2 mcp server": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"--directory",
"/path/to/nav2_mcp_server",
"nav2-mcp-server"
],
"env": {
"ROS_DOMAIN_ID": "0",
"ROS_LOCALHOST_ONLY": "1"
}
}
}
Using Docker (stdio transport)
"nav2 mcp server": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ajtudela/nav2_mcp_server"
],
"env": {
"ROS_DOMAIN_ID": "0",
"ROS_LOCALHOST_ONLY": "1"
}
}
Using HTTP transport
"nav2 mcp server": {
"type": "http",
"url": "http://localhost:3001/mcp",
"env": {
"TRANSPORT_MODE": "http",
"LOG_LEVEL": "INFO"
}
}
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。