# Debug Companion MCP

> Use this tool when you need to debug Python projects and identify failure locations. It runs pytest, extracts failure locations, and displays code context around failures, with optional fix suggestions from Gemini. Ideal for AI coding agents looking to resolve testing errors and improve code quality.

Canonical page: https://skillsregistry.net/skills/shanirap-mcp-server  
JSON: https://api.skillsregistry.net/v1/skills/shanirap-mcp-server

## Description

Enables AI coding agents to debug Python projects by running pytest, extracting failure locations, displaying code context around failures, and optionally requesting fix suggestions from Gemini.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** maps-location
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/dx4etqawmf)
- **Repository:** <https://github.com/shanirap/MCP-SERVER>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "shanirap-mcp-server"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/shanirap-mcp-server` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/shanirap-mcp-server/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt