Pipeworx para Claude Code
pipeworx-io/claude-code-plugin
Acesso a 3.300+ ferramentas de dados via single MCP gateway
Ver no GitHubMCP server que conecta Claude a 3.300+ ferramentas de dados em tempo real (SEC, USPTO, FRED, Census, Zillow, Polymarket e mais) sem carregar todos os schemas na janela de contexto. Rota automaticamente via `ask_pipeworx` para alcançar 750+ fontes de dados sob demanda.
Instalação
npx convez-ai pipeworx-io/claude-code-plugin1 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
Casos de uso
- Pesquisa de dados financeiros e SEC em tempo real
- Análise de mercado imobiliário e tendências demográficas
- Rastreamento de contratos e gastos governamentais (USAspending)
- Busca de catalisadores farmacêuticos e pipelines biotech
- Detecção de mispricing entre mercados de previsão (Polymarket, Kalshi)
- Validação de claims contra dados XBRL da SEC
Veredito

Excelente solução para quem precisa de acesso amplo a dados estruturados sem pagar o custo de context de 3.300+ schemas. O design lazy-loading é inteligente; ideal para pesquisa financeira, due diligence e análise regulatória. Tier gratuito (50 req/dia) é restritivo mas funcional para experimentação.
README
A tradução para o português deste README ainda está na fila.
Pipeworx for Claude Code
Give Claude one MCP that reaches 3,300+ live-data tools across 750+ sources — SEC filings, USPTO patents, FRED, Census, FDA, EPA, USAspending, Polymarket, Zillow, weather, and 740+ more — without loading 3,300+ tool schemas into your context window.
Install
/plugin marketplace add pipeworx-io/claude-code-plugin
/plugin install pipeworx
Try it
After install, ask Claude things like:
| Ask | What it triggers |
|---|---|
| "What just happened to Apple?" | sec_8k_recent → SEC 8-K events classified by severity |
| "Spread between Polymarket and Kalshi on the next Fed decision?" | polymarket_kalshi_spread → live cross-venue mispricing |
| "Overdue Phase 3 readouts at Moderna?" | pharma_pipeline_catalysts → biotech catalyst calendar |
| "DoD cybersecurity contracts this week?" | usa_award_search → sub-second USAspending mirror |
| "Median home value and renter share in Lubbock, TX?" | housing_market_snapshot + housing_metro_demand |
| "Unemployment rate last month?" | fred_get_series → official FRED data |
Claude picks the right tool via ask_pipeworx — no pack-name memorization required.
How it loads light
The plugin exposes ~26 meta-tools, not all 3,300+ — ask_pipeworx({question}) and friends route at runtime so you get the full catalog without paying the context tax for tools you'll never call this session.
Free tier + signup
50 calls/day anonymous, IP-bound (rotates on networks). Sign up free in 10s via GitHub for 200/day + a stable account that doesn't rotate.
Verify after install
/mcp
You should see pipeworx connected with ~26 tools.
What's loaded
ask_pipeworx— natural-language router across all 750+ sources.discover_tools— top-20 relevant tools for a task, with full schemas.entity_profile/compare_entities/recent_changes/resolve_entity— fan-out across multiple packs in one call.validate_claim— fact-check claims against SEC XBRL.remember/recall/forget— persistent memory across sessions.list_packs/search_packs/get_pack_tools/get_connection_config/get_platform_status/search_mcp_directory— browse the catalog.
The bundled skill teaches Claude when to reach for each.
Direct pack access
For a specific pack's tools loaded directly (e.g., attom_property_search without going through ask_pipeworx), add a scoped MCP entry:
{
"mcpServers": {
"pipeworx-attom": {
"type": "stdio",
"command": "npx",
"args": ["-y", "mcp-remote", "https://gateway.pipeworx.io/attom/mcp"]
}
}
}
Or a vertical bundle (e.g., ?vertical=housing for the housing-data stack).
Links
- Gateway: https://gateway.pipeworx.io
- Status: https://pipeworx.io/status
- Source: https://github.com/pipeworx-io/pipeworx
License
MIT
⭐ Star if you'd use this — helps other Claude Code users discover it.