# cerberus-mcp

> Use this tool when you need to efficiently explore large codebases and reduce LLM token usage. It provides instant call graph generation and dependency analysis through AST analysis, making it ideal for massive code exploration tasks. The cerberus-mcp server takes in codebases as input and outputs optimized call graphs and dependency maps, enabling faster and more cost-effective code analysis.

Canonical page: https://skillsregistry.net/skills/undermybelt-skill-cerberus-mcp  
JSON: https://api.skillsregistry.net/v1/skills/undermybelt-skill-cerberus-mcp

## Description

An MCP server that provides ultra-efficient code exploration through AST analysis, reducing LLM token usage by up to 95% while enabling instant call graph generation and dependency analysis for massive codebases.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/xs212zwg7s)
- **Repository:** <https://github.com/Undermybelt/skill-cerberus-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": "undermybelt-skill-cerberus-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/undermybelt-skill-cerberus-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/undermybelt-skill-cerberus-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