# Graft

> Use this tool when you need to analyze code structure and dependencies for AI-powered development tasks. Graft solves problems related to code comprehension and navigation by parsing code into a ranked dependency graph. It takes in local codebases as input and outputs a structured graph via MCP, ideal for use cases requiring deep structural understanding of code.

Canonical page: https://skillsregistry.net/skills/amaar-mc-graft  
JSON: https://api.skillsregistry.net/v1/skills/amaar-mc-graft

## Description

Local-first codebase context engine that parses code into a ranked dependency graph and serves it to AI tools via MCP for deep structural understanding.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/dgpl3dwbmg)
- **Repository:** <https://github.com/amaar-mc/graft>

## 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": "amaar-mc-graft"
    }
  }
}
```

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