Sivisa: SP
MCP serverDev toolsSivisa: SP lets your AI look up information from official sources for SP. It is hosted on the platform, so you do not run anything yourself, and each query is paid for with prepaid credit. It is grouped under development tools.
Use Sivisa: SP in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Sivisa: SP and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the sivisa sp consultar tool from Sivisa: SP
No key or account is asked for. Not verified by us yet: Ahel has not run a call through it.
Details
Available today. Use it from your connected AI after setup.
No key or account is asked for. Not verified by us yet: Ahel has not run a call through it.
Add prepaid credit to cover the per-query charges, then ask your AI to look up what you need from official SP sources. More details are in the GitHub repository at github.com/mcp-dir/sivisa_sp-mcp.
What your AI can do with it
- Look up information from official sources for SP
- Answer questions using data from official sources
- Verify details against official records
- Use official-source lookups within development work
Install Sivisa: SP
The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.
Claude Code
claude mcp add --transport http --scope user sivisa-sp 'https://api.mcp.ai/p_sivisa_sp'Run it once in your project, then open /mcp to approve any sign-in the server asks for.
Claude Desktop
https://api.mcp.ai/p_sivisa_spAdd a custom connector in Settings, paste this address, and approve the sign-in.
Cursor
cursor://anysphere.cursor-deeplink/mcp/install?name=sivisa-sp&config=eyJ1cmwiOiJodHRwczovL2FwaS5tY3AuYWkvcF9zaXZpc2Ffc3AifQ==Open the link and Cursor adds the server at that address.
ChatGPT
https://api.mcp.ai/p_sivisa_spIn Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.
Codex
codex mcp add sivisa-sp --url 'https://api.mcp.ai/p_sivisa_sp'Run it once, then sign in with codex mcp login sivisa-sp if the server asks for an account.
From the project's README
As published by mcp-dir/sivisa_sp-mcp in README.md.
Sivisa: SP para Claude, ChatGPT e agentes de IA
Sivisa: SP, consulta em fonte oficial. Hospedado pela plataforma, sem credenciais da plataforma, pague por consulta com crédito pré-pago.
- 📊 1 ferramenta
- 🔒 Somente leitura
- 💬 Funciona com qualquer cliente MCP: Claude Desktop, Cursor, VS Code, Cline, Continue
- 🔑 Login via magic-link (sem senha)
English version · Documentação completa · Skill pra agentes
Instalar em 1 clique
Claude (Web e Desktop)
A Anthropic unificou a instalação de MCPs em claude.ai/customize/connectors. O mesmo link serve pra Claude Web e Claude Desktop (basta estar logado):
Manual (se o deeplink não abrir): claude.ai/customize/connectors → + → Adicionar conector personalizado → cole Nome Sivisa: SP e URL https://api.mcp.ai/p_sivisa_sp.
Cursor
➕ Instalar Sivisa: SP no Cursor
VS Code (Copilot Chat)
➕ Instalar Sivisa: SP no VS Code
ChatGPT, Manus, OpenClaw e mais 40+ clientes
Funciona em qualquer cliente MCP que suporte MCP over HTTP. A URL do servidor é sempre:
https://api.mcp.ai/p_sivisa_sp
Detalhes por cliente: INSTALL.md.
Exemplos de uso
Consultar Sivisa: SP
1 ferramenta disponível
| Tool | Descrição |
|---|---|
sivisa_sp_consultar | Sivisa: SP, consulta em fonte oficial. |
Detalhe de cada tool: docs/ferramentas.md
Preços
Pré-pago (carteira de créditos), paga por uso. Veja docs/precos.md.
Privacidade & LGPD
- Somente leitura, nenhuma ferramenta altera dados na origem.
- Sub-processadores: o LLM host que você escolher (Claude, ChatGPT, Cursor, agente próprio). Lista completa em docs/privacidade-lgpd.md.
- Os dados retornados pelas tools são enviados ao LLM host que você escolher, sub-processador fora do nosso controle. Recomendamos planos com opt-out de treinamento.
Perguntas frequentes
O servidor é open source? O servidor é proprietário (hosted). Este repositório é o wrapper público com manifestos, docs e skills — tudo MIT.
Posso usar com agente próprio (não Claude/Cursor)?
Sim — qualquer cliente que suporte MCP over HTTP. URL: https://api.mcp.ai/p_sivisa_sp.
Suporte
Licença
MIT — veja LICENSE. O servidor MCP em api.mcp.ai/p_sivisa_sp é proprietário (hosted); este repositório (manifestos, docs, skills) é MIT.
Tools it offers (7)
What this server listed when Ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.
sivisa_sp_consultarshow_versionreport_bugconnecttoolkit_infomarketplaceauthenticate
Signals
- Last commit
- Aug 2026
Advanced
- Delivery
- sivisa_sp-mcp MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
- Item type
- mcp-server
- Key
io-github-mcp-dir-sivisa-sp-mcp- Source
- github.com/mcp-dir/sivisa_sp-mcp
- Hosted endpoint
https://api.mcp.ai/p_sivisa_sp
github.com/mcp-dir/sivisa_sp-mcp