# Consulta de Radar (PSIE/Inmetro) — how to use (mcp.ai)

Look up the metrological status of a city's speed cameras and breathalyzers in Inmetro's official records (PSIE), the same data a citizen accesses: serial number, direction, nominal speed, operator, location, validity date and verification result (approved, failed or repaired). Useful to check whether the speed camera behind a fine was approved and within validity on the ticket date. Platform-hosted, no credentials, pay per query with prepaid credit.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_psie?ms=1786764780000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `psie_consulta_municipio`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/psie`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/psie/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/psie/consulta/municipio` — Lista os instrumentos do Inmetro (radares/medidores de velocidade por padrão) de um município e a situação metrológica de cada um: Nº de Série, Sentido, Vel. Nominal, Responsável, Local, Data da Decla
  - body: { uf: string, municipio: string, tipo?: integer }

## Example prompts
- "Are the speed cameras in Tibagi/PR approved by Inmetro? Any that failed?"
- "I got a speed-camera ticket in Curitiba/PR. Check if the device was within validity."
- "List the speed meters in city X and each one's verification result."

## More
- Page: https://mcp.ai/psie
- Agent spec (llms.txt): https://mcp.ai/psie/llms.txt
- Postman collection: https://mcp.ai/psie/postman.json