Use Mission Control MCP Server in Cursor#

Overview#

This tutorial explains how to run the Mission Control MCP server and connect it to Cursor. This allows you to control robot missions using natural language prompts in Cursor’s AI chat.

It uses direct MCP configuration in ~/.cursor/mcp.json and does not require a .env file.

Tutorial Walkthrough#

  1. Confirm prerequisites:

    • Ubuntu/Linux environment (validated on Ubuntu 24.04)

    • Python 3.10+

    • Cursor installed (v2.4+ recommended)

    • Install and launch Isaac Sim using the Isaac ROS Isaac Sim Setup Guide

    • Mission Control services already launched using: Mission Control Tutorial (this bringup starts both Mission Control and Mission Dispatch)

    • The Isaac Sim setup and Mission Control tutorial bringup can be done in parallel.

  2. Verify Mission Control health:

    curl http://localhost:8050/api/v1/health
    
  3. Set up the MCP package from the mission-control repository root:

    cd app/agentic-utilities/mission-control-mcp
    python3 -m venv venv
    ./venv/bin/python -m pip install -U pip
    ./venv/bin/python -m pip install -e .
    
  4. Configure Cursor MCP directly in ~/.cursor/mcp.json (or use Cursor Settings -> Tools & MCP, which writes this file).

    https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/release-4.3/resources/isaac_ros_docs/concepts/cloud_control/cursor-settings-location.png/
    https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/release-4.3/resources/isaac_ros_docs/concepts/cloud_control/cursor-mcp-settings.png/

    Add or update this server entry with your real local paths:

    {
      "mcpServers": {
        "mission-control": {
          "command": "bash",
          "args": [
            "-lc",
            "set -euo pipefail; cd \"/ABS/PATH/TO/mission-control/app/agentic-utilities/mission-control-mcp\" && exec \"/ABS/PATH/TO/mission-control/app/agentic-utilities/mission-control-mcp/venv/bin/python\" -m mission_control_mcp.server"
          ],
          "env": {
            "MISSION_CONTROL_URL": "http://localhost:8050"
          }
        }
      }
    }
    

    Note

    Replace /ABS/PATH/TO/mission-control with your actual path. If Mission Control is remote or port-forwarded, update MISSION_CONTROL_URL accordingly.

  5. Enable the mission-control server in Cursor Settings -> Tools & MCP.

  6. Start a new chat and ask:

    Use Mission Control MCP to test the connection.

    If configured correctly, the server responds with a successful connection result.

    https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/release-4.3/resources/isaac_ros_docs/concepts/cloud_control/connection-demo.gif/

Isaac Mission Control 4.3.0 Limitations#

The following Mission Control MCP tools are not supported in Isaac Mission Control 4.3.0:

MCP Tool

Ready for Isaac Mission Control 4.3.0

submit_charging_mission

No

submit_undock_mission

No

get_detected_objects

No

get_detected_apriltags

No

visualize_route

No

get_map_info

No

list_available_maps

No

select_map

No

deploy_map_to_robot

No

submit_objective

No

cancel_objective

No

submit_pick_and_place

No

Troubleshooting#

Connection Refused#

  • Confirm Mission Control is reachable at the configured MISSION_CONTROL_URL.

Tools Do Not Appear#

  • Disable/re-enable the MCP server in Cursor settings.

  • Start a new chat.

  • Restart Cursor.

Check Server Logs#

  • /tmp/mission_control_mcp.log

Implementation References#

  • MCP server tools: app/agentic-utilities/mission-control-mcp/src/server.py

  • Mission Control API client used by MCP: app/agentic-utilities/mission-control-mcp/src/queries.py