sum_up_to
CARF: Processo
CARF: Processo for Claude, ChatGPT, and AI agents
CARF: Processo, query in official source. Hosted by the platform, no platform credentials, pay per query with prepaid credit.
π 1 tool
π Read-only
π¬ Works with any MCP client: Claude Desktop, Cursor, VS Code, Cline, Continue
π Magic-link login (no password)
English version Β· Full documentation Β· Skill for agents
Install in 1 click
Claude (Web and Desktop)
Anthropic unified MCP installation at claude.ai/customize/connectors. The same link works for Claude Web and Claude Desktop (just log in):
β Open in Claude and connect
Manual (if the deeplink doesn't open): claude.ai/customize/connectors β + β Add custom connector β paste Name CARF: Processo and URL https://api.mcp.ai/p_carf_processo.
Cursor
β Install CARF: Processo in Cursor
VS Code (Copilot Chat)
β Install CARF: Processo in VS Code
ChatGPT, Manus, OpenClaw, and 40+ more clients
Works with any MCP client that supports MCP over HTTP. The server URL is always:
https://api.mcp.ai/p_carf_processoDetails per client: INSTALL.md.
Related MCP server: smsf-rules-mcp
Usage examples
Consultar CARF: Processo1 available tool
Tool | Description |
| CARF: Processo, query in official source. |
Details for each tool: docs/ferramentas.md
Pricing
Prepaid (credit wallet), pay per use. See docs/precos.md.
Privacy & LGPD
Read-only, no tool alters data at the source.
Sub-processors: the LLM host you choose (Claude, ChatGPT, Cursor, your own agent). Full list in docs/privacidade-lgpd.md.
Data returned by the tools is sent to the LLM host you choose, a sub-processor outside our control. We recommend plans with training opt-out.
Frequently asked questions
Is the server open source? The server is proprietary (hosted). This repository is the public wrapper with manifests, docs, and skills β all MIT.
Can I use it with my own agent (not Claude/Cursor)?
Yes β any client that supports MCP over HTTP. URL: https://api.mcp.ai/p_carf_processo.
Support
π§ carf_processo@mcp.ai
π GitHub Issues
π docs/
License
MIT β see LICENSE. The MCP server at api.mcp.ai/p_carf_processo is proprietary (hosted); this repository (manifests, docs, skills) is MIT.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
Related MCP Connectors
Fundamentals, KPIs, prices, valuation, earnings and dividends for 80,000+ stocks and funds.
Order-book depth & history for Polymarket, Kalshi & Limitless. Keyless demo, key for full access.
Crypto and securities tax data: summaries, positions, lots, transactions; prepare wallet imports.
A Mentat's eye on Sui DeepBook v3: read-only market data plus desk template tools. No keys.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceProvides read-only access to Banktivity 8 personal finance databases, enabling LLM-powered summaries of transactions, balances, and spending.1-
- AlicenseAqualityCmaintenanceEnables users to look up and search Australian SMSF rules β contribution caps, total super balance and Division 296 thresholds, pension minimums and lodgment deadlines β and to compute contribution headroom, every answer carrying an ato.gov.au or legislation.gov.au citation. It is read-only and deterministic, with no model calls or network access at call time.6MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to compute exact Sri Lankan tax figures β APIT/salary tax, annual income tax, withholding tax, VAT and SSCL β under the official Inland Revenue Department rules in force on any given date since 1 January 2023. Every result is returned with precise decimal amounts and the dated IRD sources and rule versions used, so rates are never recalled from memory.19 PyPIMIT
- AlicenseBqualityBmaintenanceEstimates expected insurance payouts by matching KCD disease codes, treatments, and medical costs on receipts to enrolled policy terms, and estimates US hospital indemnity, accident, and critical illness benefits from ICD-10-CM codes and plan schedules. Calculations are deterministic and fail-closed, returning NOT_EVALUATED rather than guessing when policy terms are unverified.1129 PyPIMIT