TCU Jurisprudência

io.github.mcp-dirPublished by GitHub account mcp-dirv0.1.0Updated Oct 24, 2026

Public search of the Brazilian Federal Court of Accounts (TCU) case law: keyword search across rulin

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Lets an assistant search Brazilian Federal Court of Accounts (TCU) case law by keyword and list recent rulings, with summaries, highlighted excerpts…

What you can do
Provides two read-only tools over a hosted remote endpoint. One performs keyword search across TCU rulings, selected case law (enunciados) and súmulas, returning summaries, highlighted excerpts, the rapporteur and links to the full text. The other lists the most recent TCU rulings from official open data, paginated, with summary, rapporteur, panel, session date and links.
When to use it
Useful when an assistant needs Brazilian public audit case law: checking how the TCU has ruled on a topic such as bidding fraud or waiver of tendering, or tracking the latest decisions. Not needed for general web research or non-TCU legal sources.
Requirements
A remote MCP-over-HTTP endpoint; no local runtime or package. Works with any MCP client that supports MCP over HTTP, including Claude, Cursor, VS Code, ChatGPT and custom agents. No credentials are declared for the server itself, though the README mentions magic-link login and prepaid credit-based pricing.
Before you install
The README states pricing is prepaid, credit-wallet, pay-per-use, so usage may cost money. It also states returned data is sent to the LLM host you choose, a sub-processor outside the provider's control, and recommends plans with training opt-out. Tools are described as read-only and do not modify source data.

Installation

In SourceWeft

  1. Open TCU Jurisprudência in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.mcp-dir%2Ftcu-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "tcu-jurisprud-ncia": {
      "type": "http",
      "url": "https://api.mcp.ai/p_tcu"
    }
  }
}

README

TCU Jurisprudência

TCU Jurisprudência para Claude, ChatGPT e agentes de IA

Pesquisa pública da jurisprudência do Tribunal de Contas da União (TCU): busca por palavra-chave nos entendimentos exarados em acórdãos, na jurisprudência selecionada (enunciados) e nas súmulas, com sumário, trechos destacados, relator e links pro inteiro teor. Também lista os acórdãos mais recentes. Hospedado pela plataforma, sem credenciais.

  • 📊 2 ferramentas
  • 🔒 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):

➕ Abrir no Claude e conectar

Manual (se o deeplink não abrir): claude.ai/customize/connectors → + → Adicionar conector personalizado → cole Nome TCU Jurisprudência e URL https://api.mcp.ai/p_tcu.

Cursor

➕ Instalar TCU Jurisprudência no Cursor

VS Code (Copilot Chat)

➕ Instalar TCU Jurisprudência 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_tcu

Detalhes por cliente: INSTALL.md.

Exemplos de uso

Busque acórdãos do TCU sobre fraude em licitaçãoQuais súmulas do TCU tratam de dispensa de licitação?Mostre os acórdãos mais recentes do TCU

2 ferramentas disponíveis

ToolDescrição
tcu_buscarBusca textual (por palavra-chave) na jurisprudência do TCU.
tcu_acordaos_recentesLista os acórdãos mais recentes do TCU (dados abertos oficiais), paginado, sem palavra-chave: sumário, relator, colegiado, data da sessão e links.

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: TCU, 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_tcu.

Suporte

Licença

MIT — veja LICENSE. O servidor MCP em api.mcp.ai/p_tcu é proprietário (hosted); este repositório (manifestos, docs, skills) é MIT.

Source: README.md at commit 20df4db

Tools

8

tcu_buscar

Busca textual (por palavra-chave) na jurisprudência do TCU. Escolha a base: 'acordaos' (entendimentos exarados em acórdãos), 'jurisprudencia' (enunciados da jurisprudência selecionada) ou 'sumulas'. Retorna título, sumário/enunciado, trechos destacados (fragmentos), relator, colegiado e links pro inteiro teor.

Parametersbasetermorequirediniciotamanho

tcu_acordaos_recentes

Lista os acórdãos mais recentes do TCU (dados abertos oficiais), paginado, sem palavra-chave: sumário, relator, colegiado, data da sessão e links. Pra buscar por tema, use tcu_buscar.

Parametersinicioquantidade

show_version

Show Version

Show the current MCP platform and adapter versions.

Takes no parameters.

report_bug

Report Bug

Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.

Parameterscontextmessagerequiredconversation

connect

Connection Status

Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.

Takes no parameters.

toolkit_info

Toolkit Info

Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.

Takes no parameters.

marketplace

Marketplace

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

Parameterslimitqueryactionmcp_idmessagetool_idargumentsimmediatetier_slugprompt_bodyprompt_slugprompt_tool+11 more

authenticate

Authenticate

MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.

Parameterstoken

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts