Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

MCP server for accessing transparency data from Fiorilli SCPI portals, specifically for Paraguaçu Paulista, enabling queries on expenses, revenues, bids, contracts, transfers, personnel, and official diary.

README.md

MCP Fiorilli Transparencia

Servidor MCP para portais de transparencia com Fiorilli SCPI.

O que mudou (v3)

  • Resposta padrao em JSON estruturado (structuredContent) em todas as tools.
  • Paginacao/chunking para evitar truncamento e travamento de contexto.
  • Indexacao local do Diario Oficial com SQLite FTS5.
  • Busca do Diario baseada em indice persistente, com indexacao incremental por lotes.
  • Arquitetura MCP em tools-only (sem prompts/ e resources/).
  • analise_* removidas da superficie MCP; analises devem ser compostas no cliente consumidor.
  • Filtros locais em todas as tools de dados:
  • _pagina, _por_pagina, _cursor
  • _busca, _campos, _ordenar_por, _ordem
  • Suporte a transporte MCP por HTTP (Streamable HTTP) para deploy publico no Render.
  • Portal fixo em Paraguaçu Paulista por padrão.
  • configurar_portal endurecido para publico:
  • so altera configuracao se MCP_ALLOW_CONFIG_UPDATE=true.

Ferramentas

Conjunto atual: tools de despesas, receitas, licitacoes/contratos, transferencias, pessoal e diario oficial.

Instalacao

npm install
npm run build

Variaveis de ambiente

# Transporte MCP: stdio (default) ou http
MCP_TRANSPORT=stdio

# Porta/host para modo HTTP
PORT=3000
HOST=0.0.0.0

# Seguranca para servidor publico
MCP_ALLOW_CONFIG_UPDATE=false
MCP_ALLOWED_HOSTS=paraguacu-transparente-mcp.onrender.com,localhost,127.0.0.1

# Tuning de payload
MCP_DEFAULT_PAGE_SIZE=100
MCP_MAX_PAGE_SIZE=500
MCP_TEXT_BLOCK_CHARS=12000
MCP_TOOLS_LIST_PAGE_SIZE=200

# Tuning do Diario Oficial
MCP_DATA_DIR=/var/data/paraguacu-mcp
MCP_DIARIO_SCAN_BATCH_SIZE=8
MCP_DIARIO_SCAN_MAX_BATCHES=4
MCP_DIARIO_SCAN_TIME_BUDGET_MS=70000

Execucao local

# stdio (desktop clients)
npm start

# HTTP (Render / publico)
MCP_TRANSPORT=http npm start

Endpoints no modo HTTP:

  • POST /mcp
  • GET /mcp
  • DELETE /mcp
  • GET /health

Deploy no Render

  • Build command: npm install && npm run build
  • Start command: node dist/index.js
  • Env obrigatorias:
  • MCP_TRANSPORT=http
  • PORT (Render injeta automaticamente)
  • MCP_ALLOW_CONFIG_UPDATE=false (recomendado)
  • MCP_ALLOWED_HOSTS com o dominio publico do Render
  • Para manter o indice do Diario entre deploys/restarts, monte um disco persistente

no path usado por MCP_DATA_DIR.

Notas de output

  • O campo content traz preview textual curto.
  • O payload completo da resposta fica em structuredContent.
  • Para resultados grandes, use next_cursor (ou _pagina) para navegar sem perder dados.

Licenca

MIT

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Vector & Memory servers.