FastMCP server for Obsidian wikilink suggestions from a pre-computed knowledge g MCP server

graph-autotagger-mcp

<!-- mycelium-badges:start -->

<!-- mycelium-badges:end -->

A FastMCP server that reads a pre-computed Obsidian knowledge graph and suggests wikilinks for your notes. Designed as a companion to graphify — run graphify to build the graph, then this MCP surfaces connections as you write.

Tools

Install

Open Claude Code, paste:

/plugin marketplace add adelaidasofia/graph-autotagger-mcp /plugin install graph-autotagger-mcp@graph-autotagger-mcp

After install, set GRAPHJSONPATH (see Environment variables below) and restart Claude Code, then ask:

"Suggest wikilinks for this note: [paste note content]"

Legacy install

pip install fastmcp

1. Clone:

git clone https://github.com/adelaidasofia/graph-autotagger-mcp.git
   cd graph-autotagger-mcp

1. Set the path to your graph.json:

export GRAPH_JSON_PATH="~/vault/.graph/graph.json"

Or pass it at registration time (see below).

1. Self-test:

python3 server.py

1. Register with Claude Code:

claude mcp add graph-autotagger -s user -- \
     env GRAPH_JSON_PATH="$HOME/vault/.graph/graph.json" \
     python3 /path/to/graph-autotagger-mcp/server.py

1. Restart Claude Code, then ask:

"Suggest wikilinks for this note: [paste note content]"

Environment variables

How it works

The server loads graph.json once at startup and caches it in memory. Node labels are tokenized and matched against note content using token overlap scoring. God Nodes (top 20 by degree) get special treatment since connecting to them creates high-value cross-links.

The logsuggestiondecision tool lets you build a feedback dataset over time: accepted suggestions can be used to tune the relevance threshold; rejected ones reveal graph noise.

graph.json format

Shortened. The full README is on GitHub.