convez.ai
MCP ServerProdutividadeIntermediário
adelaidasofia

Graph Autotagger MCP

adelaidasofia/graph-autotagger-mcp

Sugira wikilinks automaticamente com base em seu grafo de conhecimento

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor FastMCP que lê um grafo de conhecimento Obsidian pré-computado e sugere wikilinks para suas notas. Funciona como complemento do graphify, oferecendo sugestões de conexões automáticas durante a escrita baseadas em sobreposição de tokens e análise de comunidades no grafo.

Instalação

$npx convez-ai adelaidasofia/graph-autotagger-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 1 dia
Versão
v0.1.0
Issues abertas
0
Contribuidores
2

Casos de uso

  • Enriquecer notas Obsidian com wikilinks automáticos
  • Descobrir conexões implícitas em bases de conhecimento
  • Rastrear decisões de sugestão para melhoria do grafo

Veredito

Ferramenta especializada e bem-arquitetada para usuários avançados de Obsidian que já mantêm grafos de conhecimento. Integração direta com graphify é elegante, mas depende de setup prévio do grafo para ser útil.

README

A tradução para o português deste README ainda está na fila.

graph-autotagger-mcp

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]"

pip install fastmcp
  1. Clone:

    git clone https://github.com/adelaidasofia/graph-autotagger-mcp.git
    cd graph-autotagger-mcp
    
  2. Set the path to your graph.json:

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

    Or pass it at registration time (see below).

  3. Self-test:

    python3 server.py
    
  4. 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
    
  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):

{
  "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.

Ver o original no GitHub

Bom para

Relacionados