Control the Severe Roblox external with an AI agent — run Luau, inspect the game, read memory, build ESP/aimbot/auto-farms, all from chat. MCP server + in-Severe Luau bridge.
View on GitHub ↗Connect Severe to any AI/LLM model of your choice. Run Luau, inspect the game, read memory, and build custom ESPs, aimbots & auto-farms — all from just prompting AI.
SevereMCP is a Model Context Protocol server that hooks Severe's Luau environment up to any AI you use — Claude, ChatGPT, Gemini, or any MCP client. Ask it to run Luau, walk the game tree, list players, read memory, or build an ESP, and it does it live in your session and reads the results back.
- server.py — the MCP server (stdio, for the AI client) and an embedded WebSocket server, in one process. - bridge.lua — runs inside Severe and uses Severe's native WebsocketClient to connect out to that server, execute the commands it receives, and send JSON results back.
The split (server = WS server, bridge = WS client) is required because Severe exposes a WebsocketClient but no HTTP request function, so the bridge can't poll an HTTP server.
Default setup: Severe and the AI client on the same PC. For two machines, see Cross-machine.
2. Add the MCP server to your AI client — pick yours below. Most use this JSON block; replace the path with your real path to server.py:
Restart Claude Code, then run claude mcp list — severe-bridge should show connected.
1. Settings → Developer → Edit Config (opens claudedesktopconfig.json). 2. Paste the JSON block above (merge into mcpServers if the file already has some). 3. Save, then fully quit and reopen Claude Desktop.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/RealSlimShady2000--SevereMCP.html)
Self-hosted semantic memory for AI Agents. Persistent sessions, experience scoring, and a graveyard for dead ends, backed by knowledge acquired from the RSS you read and stored in a Valkey vector sear
Lulu-The-Narwhal/dali-mcpCreative intelligence MCP — score your prompt before you spend the credit
NmaaAlhawary/MCP-MoodleControl Moodle from an AI assistant via MCP — read courses and build content (pages, books, quizzes) through a companion plugin + MCP server.
0xwilliamortiz/openclaude-improvedruns anywhere. uses anything
livetennisapi/livetennisapi-mcpMCP server for the Live Tennis API — give Claude, Cursor and other LLM agents real-time tennis scores, odds and model win-probability
yearningss/gamemaker-mcpA powerful, project-aware Model Context Protocol (MCP) server for GameMaker Studio with 190 tools, GML static analysis, refactoring, and automated builds.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.