convez.ai
MCP ServerIntegração & APIsIntermediário
adelaidasofia

Parse MCP – Roteador Multi-Parser

adelaidasofia/parse-mcp

Um MCP, muitos parsers. Escolhe o melhor backend automaticamente.

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP server que roteia parsing de documentos entre markitdown, Docling e LlamaParse, escolhendo o backend ideal conforme o tipo de arquivo. Inclui ferramenta `interpret` que entuba markdown parseado direto no Claude com prompt caching, eliminando malabarismo entre parsers.

Instalação

$npx convez-ai adelaidasofia/parse-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
1
Acompanhando
0
Saúde
42%
Último commit
há 1 dia
Versão
v0.2.0
Issues abertas
1
Contribuidores
2

Casos de uso

  • Extrair conteúdo de PDFs, DOCX, PPTX e URLs heterogêneas com qualidade automática
  • Processar tabelas complexas e PDFs escaneados escalando para Docling/LlamaParse
  • Resumir e extrair dados de documentos via interpret + Claude com cache
  • Chunking document-aware para RAG com detecção automática de tipo (paper, manual, QA, etc.)

Veredito

Ferramenta produtiva para quem lida com parsing heterogêneo. Design inteligente de fallback (markitdown → Docling → LlamaParse) reduz fricção. Prompt caching no interpret economiza tokens; chunking estrutural é detalhe bem pensado para RAG.

README

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

parse-mcp

One MCP, many parsers. Default markitdown (free, fast, MIT). Escalate to Docling (table-heavy, scanned PDFs) or LlamaParse (cloud, BYOK) when markitdown's quality isn't enough. Plus an interpret tool that pipes parsed markdown into Claude for "summarize / extract X" so you stop juggling parsers and anthropic skills.

Install

Open Claude Code, paste:

/plugin marketplace add adelaidasofia/parse-mcp
/plugin install parse-mcp@parse-mcp

Manual install (pre-plugin-marketplace). See SETUP.md for full details.

pip3 install --break-system-packages -r requirements.txt
pip3 install --break-system-packages 'markitdown[pdf,docx,pptx,xlsx]'

Then register the server in your client's .mcp.json:

{
  "mcpServers": {
    "parse": {
      "command": "python3",
      "args": ["/absolute/path/to/parse-mcp/server.py"]
    }
  }
}

Tools

ToolWhat it does
parse(source, backend?, hints?)File path or http(s) URL to markdown. Router picks backend, falls back on empty/error. Returns markdown plus a chain of every backend attempted.
parse_url(url, backend?)Shortcut for HTTP(S) inputs. Same return shape as parse.
parse_to_vault(source, vault_folder?, backend?, overwrite?)Parse + write the result as a markdown note in the vault. Default folder: <VAULT_ROOT>/📥 Inbox/Converted/. Frontmatter records source, format, backend, latency, bytes_in. Replaces the standalone markitdown_to_vault.py shell script.
interpret(source, instruction, backend?, model?, max_tokens?)Parse first, then ask Claude over the parsed markdown. Cache hits reuse parsed text for free input tokens.
list_backends()Which backends are installed + which are missing. Diagnostic.
benchmark(source)Run every available backend on the same input. Compare latency + output side by side.
chunk_text(text, doc_type?, target_tokens?, max_tokens?, min_tokens?)Chunk parsed markdown into retrieval-ready pieces using a doc-type-aware chunker. doc_type="auto" (default) runs structural detection and picks one of paper / book / manual / qa / resume / table / default. Each chunker honors document shape (e.g., paper keeps the abstract whole; manual never merges across numbered sections; qa pairs each question with its answer). Returns chunks + the resolved doc_type. See chunkers/ package.
detect_doc_type(text)Diagnostic. Run structural heuristics over markdown and return the doc_type that chunk_text would pick.

Backends (priority order)

  1. markitdown (default, MIT, base install). PDF, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, EPub, ZIP. Fast, deterministic.
  2. docling (optional, pip install docling). Best for complex tables (97.9% on benchmark) + scanned PDFs. Downloads model weights on first run.
  3. llamaparse (optional, BYOK, pip install llama-cloud-services + LLAMA_CLOUD_API_KEY). Cloud, cleanest output on visually-complex PDFs.

Routing strategy

  • parse(source) with no backend arg: router picks based on file format, falls back if backend errors or returns empty.
  • parse(source, backend="docling"): force a specific backend, no fallback. Diagnostic mode.
  • Unavailable backends are skipped (logged in the chain), never errored.

Architecture

FastMCP v3.2.3+, stdio transport, Python 3.13+. Registered in [VAULT_ROOT]/.mcp.json. No daemons, no listeners, no model weights downloaded by default.

See SETUP.md for install + per-backend opt-in.

Related MCPs

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

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. See LICENSE.


Full install or team version at diazroa.com.

Ver o original no GitHub

Bom para

Relacionados