# DocuMind

> DocuMind — nmdra-documind. Use this tool when you need to access and manage local documentation and code repositories, as it provides a fully local retrieval-augmented generation (RAG) agent for efficient information retrieval and generation. DocuMind solves problems related to knowledge management, code search, and documentation access, accepting natural language queries as input and outputting relevant information and code snippets. It is particularly useful in development and research contexts where local data privacy and security are crucial.

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

## Description

Fully local RAG agent built with FastMCP + ChromaDB + Ollama model.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/nmdra/DocuMind)

## 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": "nmdra-documind"
    }
  }
}
```

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