What does MCP-RoCQ integrate with?
It integrates with the Coq proof assistant (Coq Platform 8.19, 2024.10 release) through the `coqtop` executable and Coq library paths.
@angrysky56
基本信息
RoCQ (Coq Reasoning Server)
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-rocq": {
"command": "uv",
"args": [
"venv"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
MCP-RoCQ is a Model Context Protocol server that provides advanced logical reasoning capabilities through integration with the Coq proof assistant. It enables automated dependent type checking, inductive type definitions, and property proving with both custom tactics and automation.
Install the Coq Platform 8.19 (2024.10), clone the repository, set up a uv virtual environment, install the package with uv pip install -e ., and configure the server with the --coq-path and --lib-path arguments in your MCP client JSON. The server exposes three tools: type_check, define_inductive, and prove_property.
It integrates with the Coq proof assistant (Coq Platform 8.19, 2024.10 release) through the `coqtop` executable and Coq library paths.
You need the Coq Platform 8.19, Python, uv, and the cloned repository. A JSON configuration example shows paths to `coqtop.exe` and the Coq library directory.
Three main tools: `type_check` (verify a term against an expected type), `define_inductive` (define and verify inductive types), and `prove_property` (prove a logical statement using tactics and optional automation).
The README notes that while tools are shown, Claude may not use them properly due to invalid syntax, and the author suggests others may want to fix the setup. The server is experimental and contributions are welcome.
The server uses XML protocol integration for reliable structured communication with Coq.
A security scanner for your LLM agentic workflows
A Node.js–based Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.
This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent
A code reasoning MCP server, a fork of sequential-thinking
ArduPilotドローンをAIエージェントから操作するMCPサーバーです。
评论