# trace-mcp

> trace-mcp — nikolai-vysotskyi-trace-mcp. Use this tool when you need to streamline code exploration and reduce manual effort, as it replaces approximately 42 minutes of agent exploration with a single tool call, providing a efficient interface for MCP server functionality. It solves problems related to code discovery and navigation, particularly with Claude Code and Codex. Ideal for use cases involving git integration, where rapid code understanding is crucial.

Canonical page: https://skillsregistry.net/skills/nikolai-vysotskyi-trace-mcp  
JSON: https://api.skillsregistry.net/v1/skills/nikolai-vysotskyi-trace-mcp

## Description

Framework-aware code intelligence MCP server — 88 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, comprehension at parity

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/nikolai-vysotskyi/trace-mcp)

## 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": "nikolai-vysotskyi-trace-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nikolai-vysotskyi-trace-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nikolai-vysotskyi-trace-mcp/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