Graphify MCP — Casos de uso, Instalar & Demo ao vivo

Por que usar

Principais recursos

Multimodal input: code (25 languages via tree-sitter), PDF, Markdown, images, video, audio
Output: interactive HTML graph, graph.json, and Markdown report
Leiden community detection groups related concepts automatically
Slash commands: /graphify query, /graphify path, /graphify explain
Hooks integration so the graph is referenced automatically, not just on demand
--watch mode: auto-update on file changes; merge-graphs for cross-repo views

Demo ao vivo

Como fica na prática

graphify-skill.replay ▶ pronto

0/0

Instalar

Escolha seu cliente

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "graphify-skill": {
      "command": "uv",
      "args": [
        "tool",
        "install",
        "graphifyy"
      ],
      "_inferred": true
    }
  }
}

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "graphify-skill": {
      "command": "uv",
      "args": [
        "tool",
        "install",
        "graphifyy"
      ],
      "_inferred": true
    }
  }
}

Cursor usa o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "graphify-skill": {
      "command": "uv",
      "args": [
        "tool",
        "install",
        "graphifyy"
      ],
      "_inferred": true
    }
  }
}

Clique no ícone MCP Servers na barra lateral do Cline, depois "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "graphify-skill": {
      "command": "uv",
      "args": [
        "tool",
        "install",
        "graphifyy"
      ],
      "_inferred": true
    }
  }
}

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "graphify-skill",
      "command": "uv",
      "args": [
        "tool",
        "install",
        "graphifyy"
      ]
    }
  ]
}

O Continue usa um array de objetos de servidor em vez de um map.

~/.config/zed/settings.json

{
  "context_servers": {
    "graphify-skill": {
      "command": {
        "path": "uv",
        "args": [
          "tool",
          "install",
          "graphifyy"
        ]
      }
    }
  }
}

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

claude mcp add graphify-skill -- uv tool install graphifyy

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do mundo real: Graphify

Onboard to a 5-year-old legacy codebase in hours, not weeks

👤 New hires, contractors inheriting code ⏱ ~60 min intermediate

Quando usar: You've joined a project with 10k+ files, dozens of internal services, and tribal knowledge spread across PRs and Confluence.

Pré-requisitos

uv installed — curl -LsSf https://astral.sh/uv/install.sh | sh
Graphify installed globally — uv tool install graphifyy && graphify install

Fluxo

Index the repo

/graphify index /workspace/monolith --include '**/*.{ts,py,md}'✓ Copiado

→ Graph builds; report tells you cluster count and dominant concepts
Ask the graph

/graphify query 'how does payment processing connect to audit logging?'✓ Copiado

→ Path through concepts with file references — not just a grep
Open the visual

/graphify explain 'user-account cluster' and open the HTML viewer✓ Copiado

→ Interactive graph opens; cluster is highlighted with its bridges

Resultado: You know the conceptual shape of the codebase — where the hot paths live, which clusters are isolated, what depends on what.

Armadilhas

Graph becomes stale as the repo changes — graphify --watch to auto-update; or re-index before a big review session
Noise from vendored deps — Configure --exclude 'node_modules/,vendor/' on initial indexing

Combine com: filesystem · context7

Build a research graph over 200 papers and ask cross-paper questions

👤 Researchers, policy analysts, lit-review writers ⏱ ~90 min intermediate

Quando usar: You have a folder of 200 PDFs and need to find cross-paper threads no single paper exposes.

Fluxo

Index the corpus

/graphify index /research/climate-pdfs✓ Copiado

→ Concept clusters emerge (e.g. 'carbon pricing', 'adaptation finance')
Bridge-finding query

/graphify path 'adaptation finance' → 'sovereign debt'✓ Copiado

→ Ordered chain of concepts + papers that connect the two
Generate a literature review

Summarize the 'adaptation finance → sovereign debt' bridge as a 400-word section with paper citations.✓ Copiado

→ Draft paragraph with correct citations from the graph

Resultado: Insights that come from the structure of the corpus, not just keyword grep.

Armadilhas

Scanned PDFs don't OCR — Run OCR (ocrmypdf) before indexing; Graphify won't magic-text images

Combine com: filesystem

Merge graphs from multiple repos into one searchable view

👤 Platform teams owning microservice fleets ⏱ ~120 min advanced

Quando usar: You run 15 services. You want one graph that spans them so an agent can follow a request end-to-end.

Fluxo

Index each service

For each repo under /services/, run graphify index with --out graph-<name>.json✓ Copiado

→ 15 graph.json files on disk
Merge

graphify merge-graphs graph-*.json --out fleet.json✓ Copiado

→ One unified graph with cross-repo edges
Ask end-to-end

/graphify query 'trace a POST /checkout through the fleet'✓ Copiado

→ Path through multiple services, each node annotated with its repo

Resultado: Cross-service traceability without a service mesh or OTEL rollout.

Armadilhas

Same concept named differently across repos — Graphify's similarity merge handles most; for the rest, define aliases in the config

Combine com: filesystem · github

Combinações

Combine com outros MCPs para 10× de alavancagem

graphify-skill + filesystem

Graphify points at files; filesystem lets the agent actually read/edit them

/graphify query 'retry logic' → list files, then filesystem read_text_file each one to draft a refactor.✓ Copiado

graphify-skill + github

Turn graph queries into PR plans

Use the graph to find everywhere we do ad-hoc retries; open a GitHub issue listing each file with a proposed consolidation.✓ Copiado

graphify-skill + sequential-thinking

Multi-step reasoning that uses the graph as an oracle

Plan the refactor step-by-step; at each step, consult /graphify query for impact.✓ Copiado

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar	Custo
/graphify index	path, include, exclude, --watch	First — build the graph	Claude calls for concept extraction (use prompt caching)
/graphify query	natural-language question	The primary query interface	free (local) + small model call
/graphify path	concept A → concept B	When you want to see how two ideas connect	free
/graphify explain	node/cluster id	Deep-dive on a single cluster	free + small model call
graphify merge-graphs	graph-*.json	Cross-repo / cross-folder views	free

Custo e limites

O que custa rodar

Cota de API: Local indexing is free; concept extraction uses Claude API (your key)
Tokens por chamada: Indexing a 10k-file repo ≈ tens of dollars with caching; queries are cheap
Monetário: Free software; pay for the extraction calls only
Dica: Cache aggressively — Graphify already does prompt caching for extraction; index once, query 1000x

Segurança

Permissões, segredos, alcance

Armazenamento de credenciais: Uses your Claude API key for extraction; graph.json stored locally

Saída de dados: Concept extraction calls go to Anthropic (your account). No telemetry from Graphify itself.

Nunca conceda: Sharing graph.json publicly when indexed from a private repo — it embeds code snippets and filenames

graph.json can contain sensitive snippets. .gitignore it unless you want the graph shared with the repo.
--watch spawns file-system watchers; on huge repos, set include/exclude to avoid pegging a CPU.

Solução de problemas

Erros comuns e correções

graphify: command not found after install

uv tool install graphifyy puts the binary in ~/.local/bin; ensure that's on PATH, or run with uv tool run graphify.

Verificar: uv tool list | grep graphify

Indexing takes forever on a large repo

Scope with --include '**/*.{py,ts,md}' and --exclude 'node_modules/,dist/'. Concept extraction, not parsing, is the bottleneck.

Verificar: Watch the progress log; parsing should be seconds, extraction takes the time

Queries return irrelevant clusters

Graph quality depends on the index — add README/docs files to the input set so Claude has project context for naming clusters

Verificar: Rebuild including /docs/**/*.md; queries should sharpen

Merge-graphs produces duplicate nodes

Lower --similarity-threshold (default ~0.8) to 0.7 to merge near-duplicates more aggressively; tune per-repo

Alternativas

Graphify vs. outros

Alternativa	Quando usar	Troca
Serena	You want LSP-precise symbol navigation and refactor tools, not conceptual clusters	No multi-modal input; no clustering
Memory MCP	You want Claude to remember session facts, not index a corpus	No graph; no query-by-concept
Raw embedding + vector DB	You need custom retrieval logic and don't care about community detection	You build the whole pipeline — graphify is opinionated and faster to ship

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills