# DocGraph

> DocGraph — detective-xh-docgraph. Use this tool when you need to efficiently organize and search large collections of documentation files, such as .md, .docx, .html, and .pdf, to provide LLM agents with a knowledge graph for informed decision-making. DocGraph solves problems of information overload and knowledge discovery by indexing files into SQLite and offering 12 MCP tools, including full-text search and topic similarity. It is ideal for use cases involving research, governance, and content management, particularly in git-based workflows.

Canonical page: https://skillsregistry.net/skills/detective-xh-docgraph  
JSON: https://api.skillsregistry.net/v1/skills/detective-xh-docgraph

## Description

Govern your documents like code. MCP server that indexes .md/.docx/.html/.pdf into a SQLite knowledge graph and runs drift audits — stale policies, conflicting research claims, superseded docs, undocumented code exports. 12 MCP tools incl. cross-reference graph, governance + provenance metadata, topic similarity. Single binary, zero runtime deps.

## Trust

- **Trust score (0–1):** 0.61
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/Detective-XH/DocGraph)

## 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": "detective-xh-docgraph"
    }
  }
}
```

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