# Librarian

> Use this tool when you need to integrate AI assistants with local knowledge bases, such as Obsidian vaults or markdown folders, to enable full-text search, file management, and graph analysis. It solves problems related to knowledge retrieval, organization, and visualization, and provides inputs such as markdown files and outputs like graph visualizations and community detections. Ideal for use cases where local data privacy is essential and AI-driven insights are needed to navigate complex knowledge networks.

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

## Description

Librarian provides AI assistants with deep access to Obsidian vaults and markdown folders. It supports full-text search, file read/write with automatic wikilink detection, backlink and tag exploration, graph traversal with shortest-path finding, community detection via Louvain optimization, and D3.js visualizations. Works with any markdown folder without requiring Obsidian to be running, and all data stays local.

## Trust

- **Trust score (0–1):** 0.78
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/ngmeyer-librarian)
- **Repository:** <https://github.com/ngmeyer/librarian-mcp>

## 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": "ngmeyer-librarian"
    }
  }
}
```

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