yade-mcp
O.engines += [LLM()] # yet another engine.
yade-mcp connects AI agents to YADE — the open-source discrete element method engine — through the Model Context Protocol. Browse API docs, run simulations, and execute code, all through natural conversation.

Tools (7)
2 documentation tools — browse and search the YADE Python API with BM25 keyword search. No bridge required.
5 execution tools — synchronous REPL, async task submission, progress monitoring, interruption, and task history. Requires bridge.
Quick Start
Prerequisites
Agentic Setup (Recommended)
Copy this to your AI agent and let it self-configure:
Fetch and follow this bootstrap guide end-to-end:
https://raw.githubusercontent.com/yusong652/yade-mcp/master/docs/agentic/yade-mcp-bootstrap.md
Manual Setup
1. Register the MCP server in your client config:
{
"mcpServers": {
"yade-mcp": {
"command": "uvx",
"args": ["yade-mcp"]
}
}
}
2. Start the bridge inside YADE:
pip install yade-mcp-bridge
Then in a YADE Python console:
import yade_mcp_bridge
yade_mcp_bridge.start()
Verify
Restart your AI agent (Claude Code, Codex CLI, Gemini CLI, etc.) and ask it to call yade_execute_code to verify the connection.
Features
- Rich class documentation — covers the YADE Python API, enriched with real types, defaults, and docstrings
- Hierarchical API browsing — agents navigate categories, subcategories, and classes with progressive disclosure, reducing hallucination
- BM25 keyword search — fast, ranked search across all API docs by natural language queries
- Synchronous REPL — rapid iteration for querying simulation state (
O.bodies,O.iter, quick tests) - Async task lifecycle — submit long-running simulations, monitor progress, gracefully interrupt via PyRunner, and browse history
- Multi-client compatible — works with Claude Code, Codex CLI, Gemini CLI, OpenCode, and other MCP clients
Contributing
See CONTRIBUTING.md for development setup and guidelines.
License
MIT — see LICENSE.