npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

obsidian-graph-memory

v1.0.1

Published

MCP server exposing Obsidian vault graph structure as queryable tools

Readme

obsidian-graph-memory

An MCP server that exposes your Obsidian vault's graph structure as queryable tools for AI agents. It connects to the Obsidian Local REST API plugin, builds an in-memory graph of notes and wikilinks, and lets agents traverse relationships, find paths, discover hubs, and more.

Installation

As an MCP server (recommended)

Add to your Claude Code config (~/.claude.json):

{
  "mcpServers": {
    "graph-memory": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "obsidian-graph-memory"],
      "env": {
        "OBSIDIAN_API_KEY": "your-api-key",
        "OBSIDIAN_HOST": "http://localhost:27124"
      }
    }
  }
}

Global install

npm install -g obsidian-graph-memory

Run directly

npx obsidian-graph-memory

Prerequisites

Environment Variables

| Variable | Required | Default | Description | |---|---|---|---| | OBSIDIAN_API_KEY | Yes | — | API key from the Local REST API plugin | | OBSIDIAN_HOST | No | http://localhost:27123 | URL of the Obsidian REST API | | GRAPH_REFRESH_INTERVAL | No | 5m | Auto-refresh interval (e.g. 30s, 5m, 1h) |

Tools

graph_query_related

Find notes within N hops of a given note via wikilinks. Use for context expansion — "what's related to X?"

| Parameter | Type | Required | Description | |---|---|---|---| | note | string | Yes | Name of the note (without .md extension) | | depth | number | No | How many hops to traverse (1-3, default: 1) |

graph_find_path

Find the shortest path between two notes via wikilinks. Use to discover connections — "how does A relate to B?"

| Parameter | Type | Required | Description | |---|---|---|---| | from | string | Yes | Starting note name | | to | string | Yes | Target note name |

graph_get_hubs

Get the most connected notes in the vault. Use to find central knowledge — "what are the key topics?"

| Parameter | Type | Required | Description | |---|---|---|---| | topN | number | No | Number of top hubs to return (1-50, default: 10) |

graph_get_orphans

Get notes with zero links (neither linking to nor linked from any other note). Use to find gaps — "what's disconnected?"

No parameters.

graph_get_clusters

Group notes by folder or tag. Use for topic overview — "what topics exist in the vault?"

| Parameter | Type | Required | Description | |---|---|---|---| | by | string | No | Group by folder or tag (default: folder) |

graph_get_stats

Get vault-wide statistics: note count, link count, tags, orphans, etc. Quick status check.

No parameters.

graph_refresh

Manually trigger a graph rebuild from the vault. Use after batch changes to notes.

No parameters.

How It Works

  1. On startup, the server fetches all markdown files from your vault via the Obsidian REST API
  2. It parses each note for [[wikilinks]] and #tags (both frontmatter and inline)
  3. An in-memory directed graph is built — nodes are notes, edges are wikilinks
  4. Graph queries use BFS traversal following both outgoing and incoming links
  5. The graph auto-refreshes on a configurable interval (default: 5 minutes)

License

MIT