# codesteward

> Use this tool when you need to analyze and query complex code structures, as it parses repositories into a graph database, solving problems related to code comprehension and dependency management. It takes in git repositories as input and provides outputs through lexical, referential, semantic, and dependency queries via the MCP tool interface. Use codesteward in contexts where AI agents require in-depth code insights, such as automated code review or intelligent coding assistance.

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

## Description

Structural code graph server for AI agents — parses repositories into a Neo4j graph via tree-sitter and exposes it as an MCP tool interface with lexical, referential, semantic, and dependency queries.

## Trust

- **Trust score (0–1):** 0.94
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [GitHub](https://github.com/Codesteward/codesteward)

## 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": "codesteward-codesteward"
    }
  }
}
```

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