# ROS MCP server

> Connect LLMs to ROS and ROS 2 robots to work with topics, services, actions and parameters through rosbridge.

- Listing: https://mcp.tc/i/ros
- Connect: this is a local (stdio) server; install it on your machine (see Install). The listing link is a page, not an MCP endpoint.
- Type: local (stdio)
- Auth: no API key needed
- Category: [Developer Tools](https://mcp.tc/c/developer-tools)
- Vendor: robotmcp
- Homepage: <https://robotmcp.ai>
- Repository: <https://github.com/robotmcp/ros-mcp-server>
- Package: pypi `ros-mcp`

## About

ROS MCP Server lets an AI assistant control and observe robots running ROS 1 or ROS 2. It can publish and subscribe to topics, call services and actions, set parameters, read sensor data and monitor robot state. It helps the model discover available topics, services and actions, including custom types, and use them with the right syntax.

It runs locally over stdio as the PyPI package ros-mcp, started with uvx. It talks to the robot through a rosbridge WebSocket node, so no changes to existing robot code are needed. No sign-in or API key is required. It works with MCP clients such as Claude Code, Claude Desktop, Cursor, Codex CLI and Gemini CLI.

## What it can do

- Publish and subscribe to ROS topics
- Call ROS services and actions
- Read and set robot parameters
- Read sensor data and monitor robot state
- Discover topics, services and custom message types
- Works with ROS 1 and ROS 2 distributions

## Example prompts

- "List all topics available on my robot and show their message types."
- "Subscribe to the lidar topic and tell me if anything is close to the robot."
- "Call the gripper service and check whether the end effector responds correctly."
- "Read the current navigation parameters and summarize them."

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport stdio ros -- uvx ros-mcp --transport=stdio
```

2. Start Claude Code and type `/mcp`. **ros** should show as connected.

Add `--scope user` to make it available in every project.

### Claude Desktop

1. Open **Settings → Developer → Edit Config**. It opens `claude_desktop_config.json`. Add:

`claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "ros": {
      "command": "uvx",
      "args": [
        "ros-mcp",
        "--transport=stdio"
      ]
    }
  }
}
```

2. Save the file and restart Claude Desktop.

Needs uv (Python) on your computer. The file lives in `~/Library/Application Support/Claude/` on macOS and `%APPDATA%\Claude\` on Windows.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=ros&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJyb3MtbWNwIiwiLS10cmFuc3BvcnQ9c3RkaW8iXX0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "ros": {
      "command": "uvx",
      "args": [
        "ros-mcp",
        "--transport=stdio"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=ros&config=%7B%22type%22%3A%22stdio%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22ros-mcp%22%2C%22--transport%3Dstdio%22%5D%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"ros","type":"stdio","command":"uvx","args":["ros-mcp","--transport=stdio"]}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "ros": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "ros-mcp",
        "--transport=stdio"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "ros": {
      "command": "uvx",
      "args": [
        "ros-mcp",
        "--transport=stdio"
      ]
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

### Codex

```bash
codex mcp add ros -- uvx ros-mcp --transport=stdio
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.ros]
command = "uvx"
args = ["ros-mcp", "--transport=stdio"]
```

Needs uv (Python) on your computer.

### Gemini CLI

```bash
gemini mcp add ros uvx -- ros-mcp --transport=stdio
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients that start local servers accept this shape:

```json
{
  "mcpServers": {
    "ros": {
      "command": "uvx",
      "args": [
        "ros-mcp",
        "--transport=stdio"
      ]
    }
  }
}
```

Zed puts servers under `context_servers` in its settings, with the same `command`, `args` and `env` fields.

Needs uv (Python) on your computer.

## Details

- Server version: 3.1.2
- Last checked: 2026-10-03
- Listed: 2026-10-03
- Updated: 2026-10-03

---
Source: https://mcp.tc/i/ros (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report