# codegraph-ai

> Use this tool when you need to efficiently analyze and understand complex codebases with dependency graphs, reducing token usage and improving AI agent performance. It serves structured code context via MCP, enabling agents to navigate and comprehend code relationships. Ideal for use cases where codebase complexity and token limitations hinder AI-driven development and maintenance tasks.

Canonical page: https://skillsregistry.net/skills/jotaseme-codegraph  
JSON: https://api.skillsregistry.net/v1/skills/jotaseme-codegraph

## Description

Serves structured code context via MCP, enabling AI agents to understand codebases with dependency graphs and significantly reduce token usage.

## Trust

- **Trust score (0–1):** 0.67
- **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/fhv7ygsyii)
- **Repository:** <https://github.com/jotaseme/codegraph>

## 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": "jotaseme-codegraph"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jotaseme-codegraph` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jotaseme-codegraph/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