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

io.github.adelaidasofiaPublished by GitHub account adelaidasofiav0.1.0Updated Oct 24, 2026

FastMCP server for Obsidian wikilink suggestions from a pre-computed knowledge graph (graphify…

The publisher's own server: Fastio

VerifiedSTDIODesktop onlyProductivity & WorkflowKnowledge & Memory

Overview

AI-generated overview

A local MCP server that reads a pre-computed Obsidian knowledge graph and suggests wikilinks, god nodes and communities for a note.

What you can do
Suggest wikilinks for a note by matching its content against graph node labels via token overlap, with extra weight on highly connected nodes (top 20 by degree). Identify which graph communities a note most closely belongs to. Log accepted, rejected or ignored suggestions to a local SQLite database to build a feedback dataset over time. The graph is loaded once at startup and cached in memory.
When to use it
Useful when you write in Obsidian and already have a graphify-generated graph.json, and want an assistant to propose cross-links and community placement while drafting notes. Not useful without a pre-computed graph.
Requirements
Runs as a local process (stdio) on the desktop, installed as an MCP bundle or via a Python/FastMCP setup. Requires GRAPH_JSON_PATH pointing to a graphify graph.json in networkx node_link_data format; AUTOTAGGER_DB optionally sets the SQLite log path.
Before you install
The README states the plugin sends an anonymous install signal to an external site on first load per machine, including plugin name and version; opt out with MYCELIUM_NO_PING=1. The decision log writes to a local SQLite file. Note content is matched locally against the graph.

Installation

In SourceWeft

  1. Open FastMCP server for Obsidian wikilink suggestions from a pre-computed knowledge g in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

graph-autotagger-mcp

[License] [GitHub stars] [Last commit] [Open issues] [PyPI version] [PyPI downloads] [Built by Mycelium AI]

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

ToolWhat it does
suggest_linksSuggest wikilinks for a note based on token overlap with graph node labels
check_god_nodesCheck which highly-connected nodes (top 20 by degree) are relevant to the note
community_matchFind which graph communities the note most closely belongs to
log_suggestion_decisionLog accepted/rejected/ignored decisions to a local SQLite database

Install

Open Claude Code, paste:

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

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

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

Legacy install
bash
pip install fastmcp

  1. Clone:

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

  2. Set the path to your graph.json:

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

    Or pass it at registration time (see below).

  3. Self-test:

    bash
    python3 server.py

  4. Register with Claude Code:

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

  5. Restart Claude Code, then ask:

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

Environment variables

VariableDefaultDescription
GRAPH_JSON_PATH~/vault/.graph/graph.jsonPath to your graphify output
AUTOTAGGER_DB~/.config/graph-autotagger/log.dbSQLite log for suggestion decisions

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 log_suggestion_decision 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

Expects the output format from graphify (networkx node_link_data):

json
{  "nodes": [{"id": "node-id", "label": "Node Label", "community": 0}],  "links": [{"source": "node-a", "target": "node-b"}]}

Note: networkx serializes edges under "links", not "edges".

Related MCPs

Same author, same architecture pattern (FastMCP, draft+confirm on writes where applicable, vault auto-export, MIT):

Telemetry

This plugin sends a single anonymous install signal to myceliumai.co the first time it loads in a Claude Code session on a given machine.

What is sent:

  • Plugin name (e.g. slack-mcp)
  • Plugin version (e.g. 0.1.0)

What is NOT sent:

  • No user identifiers, names, emails, tokens, or API keys
  • No file paths, message content, or anything from your work
  • No IP address is stored after dedup processing

Why: Helps the maintainer know which plugins people actually install, so attention goes to the ones that get used.

Opt out: Set the environment variable MYCELIUM_NO_PING=1 before launching Claude Code. The hook will skip the network call entirely. Already-pinged installs leave a sentinel at ~/.mycelium/onboarded-<plugin> — delete it if you want to reset state.

License

MIT

Built by Mycelium AI. Full install or team version at diazroa.com.

Source: README.md at commit 5da031e

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Fast integrations

Fastio

io.fastOfficial publisher

Fastio is a remote MCP endpoint that gives a project one workspace for its files, its team, and its AI agents.

Streamable HTTPWeb executableAuth
Files & StorageCredential requiredNov 5, 2026

Fast Entity Filing USDOT BOC-3 & 2027 UCR Compliance

com.fastentityfiling

Fast Entity Filing USDOT BOC-3 & 2027 UCR Compliance's hosted MCP server, published by fastentityfiling.com; no sign-in required; Streamable HTTP; 10 tools.

Streamable HTTPWeb executable
10 toolsNov 4, 2026

Make Agent Fast

Published by GitHub account abdurshd

Remote MCP server for Make Agent Fast that lets an assistant build customer-service agents, review conversations and leads, and improve answers.

Streamable HTTPWeb executableAuth
Business & CommerceCredential requiredOct 26, 2026

FastOCR

Published by GitHub account fastocr-org

FastOCR OCRs local scanned PDFs and images into text or searchable PDFs, and extracts bank statements into Excel, CSV or QuickBooks files.

STDIODesktop only
Files & Storage8 toolsNov 7, 2026

Fast Data Actors (via Apify MCP)

Published by GitHub account ichkifokkus

A configuration for Apify's hosted MCP server that exposes Fast Data Actors for YouTube transcripts, Google News/Trends, job postings, document conversion and…

Streamable HTTPWeb executableAuth
Web Search & ScrapingCredential requiredOct 26, 2026