Capivara: Investigação Cadastral
RemoteAbout Capivara: Investigação Cadastral
Capivara is a hosted, read-only MCP server for producing consolidated background reports on people or companies from CPF or CNPJ data. It is intended for legal and investigative research, with identity discovery, consent records, and reports covering areas such as credit, sanctions, vehicles, and court cases.
Key features
- 01Identity discovery from free-text clues
- 02Auditable investigation consent records
- 03Consolidated person and company reports
- 04Three investigation tools
- 05Hosted service with prepaid credits
Use cases
- 01Identify a person from name, city, or work clues
- 02Review a person's credit and sanctions
- 03Compile company ownership and court-case information
MCP support
Exposes three tools to MCP clients for identity resolution, consent recording, and dossier creation. It works with MCP over HTTP.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.mcp.ai/p_capivaraclaude mcp add --transport http dir-capivara https://api.mcp.ai/p_capivara{"mcpServers":{"dir-capivara":{"type":"http","url":"https://api.mcp.ai/p_capivara"}}}Open in Cursor{"servers":{"dir-capivara":{"type":"http","url":"https://api.mcp.ai/p_capivara"}}}Open in VS Code{"mcpServers":{"dir-capivara":{"type":"http","url":"https://api.mcp.ai/p_capivara"}}}{"mcpServers":{"dir-capivara":{"serverUrl":"https://api.mcp.ai/p_capivara"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
9| Parameter | Type | Required | Description |
|---|---|---|---|
| cnpj | string | No | |
| nivel | enum | No | basico | medio | avancado |
| texto | string | No | |
| seguir_dossie | boolean | No |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.