Scan an MCP server
Paste the URL of a remote MCP server. We connect the way an agent would, read its tools and instructions, and look for text written to steer the agent. We never call a tool.
The Streamable HTTP endpoint, often ending in /mcp. Don't paste a URL that contains an API key or token: the link to the report includes the URL.
MCP 14 Oct 2026, 12:38 UTC
api.mcp.ai/
No findings. Our rules found nothing in its tools or instructions aimed at steering an agent.
0 high, 0 medium, 0 low. Link to this scan
Passed: Served over HTTPS.
Passed: Answered in 671 ms, protocol 2025-06-18.
Passed: Lists its tools without credentials.
Note: Read 7 tools and the server instructions.
Passed: Tool names and descriptions match our last check (3 hours ago).
The tools as an agent sees them
Written by the server, not by ToolVet. Descriptions are shortened.
- tribunal_trt_processo_consultar
Tribunal TRT: Consulta Processual Unificada, consulta em fonte oficial. Hospedado pela plataforma, sem credenciais da plataforma, pague por consulta com crédito pré-pago. Consulta informação de fontes e órgãos oficiais brasileiros (a mesma disponível ao cidadão), não é dado sigiloso. O cliente é o controlador dos dados e responde pela finalidade legítima (LGPD).
- show_version
Show the current MCP platform and adapter versions.
- report_bug
Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
- connect
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.
- 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.
- 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.
- 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.
Show your score
Put the badge in your README or docs. It links to the listing and updates as the score changes.
Markdown, for a README:
[](https://toolvet.app/s/tribunal-trt-consulta-processual-unificada)HTML, for a website:
<a href="https://toolvet.app/s/tribunal-trt-consulta-processual-unificada"><img src="https://toolvet.app/badge/tribunal-trt-consulta-processual-unificada.svg" alt="ToolVet trust score" height="20"></a>What this scan covers
One connection, the way an agent sees the server: its tool definitions and instructions. It doesn't call tools or send credentials, and it uses fixed rules, so no findings is not a guarantee. How the grade works. If a finding is wrong, tell us with the link to this scan at [email protected].