Allows AI agents to control Roblox Studio via HTTP requests, enabling scripted interactions with the Studio environment.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@roblox-mcp-bridge list available studio tools"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP bridge that connects Roblox Studio to local AI agents
Open Roblox Studio.
Open any project and navigate to the Assistant panel.
Click the three dots (...), select Manage MCP Servers, and ensure the option is enabled.
Locate and copy the absolute path to your local mcp.bat file.
Clone this repository to your local machine.
Edit config.json and paste your absolute path into the ROBLOX_MCP_PATH variable.
Double-click run.bat to automatically build the virtual environment, install dependencies, and launch the server.
Once the bridge is running, any AI agent or local script can control Roblox Studio by sending HTTP requests to the server.
Before running commands, contact the bridge to see which functions your current version of Roblox Studio exposes.
cURL:
curl -X GET [http://127.0.0.1:8000/tools](http://127.0.0.1:8000/tools)This server cannot be deployed
Connect AI agents to Replynodes over the Model Context Protocol.
Connect AI agents to Flato's editable canvas runtime through a hosted MCP server.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Connect AI agents to Process Street workflows, tasks, runs, data sets, and operational records.
