About CARF (Recursos Fiscais)
An MCP server for tax-law research that searches CARF rulings and summaries, proceedings by CPF or CNPJ, and case law from 16 other Brazilian courts. It provides official-source links and notes that CARF decisions do not bind judges.
Key features
- 01Search rulings and summaries by topic
- 02Find CARF cases by CPF or CNPJ
- 03Search 16 other Brazilian courts
- 04Read full decision texts
- 05Provide official-source links
- 06Flag the decisions' judicial status
Use cases
- 01Research CARF positions on tax disputes
- 02Find CARF proceedings by CPF or CNPJ
- 03Compare CARF and court treatment of a topic
MCP support
Exposes tools for case-law and summary search, full decision retrieval, and CARF proceeding lookup. Case-law and summary searches are free; proceeding lookups are pay-per-query.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.mcp.ai/p_carfclaude mcp add --transport http dir-carf https://api.mcp.ai/p_carf{"mcpServers":{"dir-carf":{"type":"http","url":"https://api.mcp.ai/p_carf"}}}Open in Cursor{"servers":{"dir-carf":{"type":"http","url":"https://api.mcp.ai/p_carf"}}}Open in VS Code{"mcpServers":{"dir-carf":{"type":"http","url":"https://api.mcp.ai/p_carf"}}}{"mcpServers":{"dir-carf":{"serverUrl":"https://api.mcp.ai/p_carf"}}}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
10| Parameter | Type | Required | Description |
|---|---|---|---|
| max | number | No | |
| tipo | string | No | |
| termo | string | Yes | |
| data_de | string | No | |
| ordenar | enum | No | relevancia | recencia |
| data_ate | string | No | |
| tribunais | array | 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.