SkillAgentSearch skills...

mcp-rocq

RoCQ (Coq Reasoning Server)

Install / Use

claude mcp add angrysky56 -- npx -y github:angrysky56/mcp-rocq

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

59/100

Supported Platforms

Claude Code
Claude Desktop

Tags

Our assessment of mcp-rocq

mcp-rocq scores 59/100 on our quality scale, 4164th of 4,645 Development & Engineering skills we index.

Its MCP Server is 2.9 KB long, well organised into 11 sections with 7 code examples: a solid amount of guidance for an agent.

It has 10 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
26/30
Structure
20/20
Description
4/15
Adoption
4/20
Freshness
5/15

Maintenance, license and trust

  • The repository was last updated about 1.8 years ago. Expect some instructions to reference tool versions or APIs that have since changed.
  • Our last check on 2026-10-21 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 80/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

mcp-rocq compared with similar skills

All 4 of these similar skills score higher than mcp-rocq; compare them before choosing.

SkillScoreStarsUpdatedFormat
mcp-rocq (this skill)by angrysky56591022mo agoMCP Server
taste-skillby Leonxlnx100111.4k2d agoCLAUDE.md
Agent-Reachby Panniantong100109.8k1d agoCLAUDE.md
headroomby headroomlabs-ai10079.1ktodayCLAUDE.md
ai-job-searchby ai-job-search-dev10070.2k2d agoCLAUDE.md

Frequently asked questions

How do I install mcp-rocq?
Run claude mcp add angrysky56 -- npx -y github:angrysky56/mcp-rocq. The install tabs above show the steps for each supported agent.
Which AI agents does mcp-rocq work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is mcp-rocq safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 80/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is mcp-rocq still maintained?
The repository was last updated about 1.8 years ago. Expect some instructions to reference tool versions or APIs that have since changed.

MCP-RoCQ (Coq Reasoning Server)

Currently shows tools but Claude can't use it properly for some reason- invalid syntax generally seems the issue but there could be something else.

There may be a better way to set this up with the coq cli or something. Anyone want to try and fix it who knows what they are doing would be great.

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.

Features

  • Automated Dependent Type Checking: Verify terms against complex dependent types
  • Inductive Type Definition: Define and automatically verify custom inductive data types
  • Property Proving: Prove logical properties using custom tactics and automation
  • XML Protocol Integration: Reliable structured communication with Coq
  • Rich Error Handling: Detailed feedback for type errors and failed proofs

Installation

  1. Install the Coq Platform 8.19 (2024.10)

Coq is a formal proof management system. It provides a formal language to write mathematical definitions, executable algorithms and theorems together with an environment for semi-interactive development of machine-checked proofs.

https://github.com/coq/platform

  1. Clone this repository:
git clone https://github.com/angrysky56/mcp-rocq.git

cd to the repo

uv venv
./venv/Scripts/activate
uv pip install -e .

JSON for the Claude App or mcphost config- set your paths according to how you installed coq and the repository.

    "mcp-rocq": {
      "command": "uv",
      "args": [
        "--directory",
        "F:/GithubRepos/mcp-rocq",
        "run",
        "mcp_rocq",
        "--coq-path",
        "F:/Coq-Platform~8.19~2024.10/bin/coqtop.exe",
        "--lib-path",
        "F:/Coq-Platform~8.19~2024.10/lib/coq"
      ]
    },

This might work- I got it going with uv and most of this could be hallucinatory though:

  1. Install dependencies:
pip install -r requirements.txt

Usage

The server provides three main capabilities:

1. Type Checking

{
    "tool": "type_check",
    "args": {
        "term": "<term to check>",
        "expected_type": "<type>",
        "context": ["relevant", "modules"] 
    }
}

2. Inductive Types

{
    "tool": "define_inductive",
    "args": {
        "name": "Tree",
        "constructors": [
            "Leaf : Tree",
            "Node : Tree -> Tree -> Tree"
        ],
        "verify": true
    }
}

3. Property Proving

{
    "tool": "prove_property",
    "args": {
        "property": "<statement>",
        "tactics": ["<tactic sequence>"],
        "use_automation": true
    }
}

License

This project is licensed under the MIT License - see the LICENSE file for details.

Related Skills

View on GitHub
GitHub Stars10
CategoryDevelopment
Updated1y ago
Forks4

Languages

Python

Trust signals

80/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium1 low1 info