# CPFL: Download + OCR [Health: Active]

**Category:** 💻 Developer Tools  
**Repository:** https://github.com/mcp-dir/contas_cpfl_download_ocr-mcp  
**GitHub Stars:** 0  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/cpfl-download-ocr

## Description
CPFL: Download + OCR, official-source lookup. Platform-hosted, pay per query with prepaid credit.

## Tools
Capabilities this server exposes over MCP:

- **contas_cpfl_download_ocr_consultar** — CPFL: Download + OCR, 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. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.
- **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.

## Claude Desktop Quick Installation
Remote MCP endpoint (confidence: high). Install path detected from listing signals. Add as a URL/SSE server in your client:

```json
"mcpServers": {
  "cpfl-download-ocr": {
    "url": "https://api.mcp.ai/p_contas_cpfl_download_ocr"
  }
}
```

## Documentation

## What CPFL: Download + OCR does

CPFL: Download + OCR provides an MCP connection to a hosted service for CPFL lookups using an official source. The service is designed for AI clients and agents that need to request this operation through MCP rather than through a separate application interface.

The CPFL: Download + OCR package exposes one operation: `contas_cpfl_download_ocr_consultar`. The repository describes the operation as an official-source consultation and identifies the server as read-only. It does not provide tools that modify records or data at the source.

## How it works

The hosted endpoint is available at `https://api.mcp.ai/p_contas_cpfl_download_ocr`. An MCP-compatible client sends requests to that URL over MCP over HTTP, and the service handles the hosted lookup. The server does not require credentials for the hosting platform. User access is handled through a passwordless magic link.

Because the service is hosted, the repository functions as a public wrapper containing manifests, documentation, and agent skills; the hosted MCP server itself is proprietary. Requests use a prepaid credit wallet, with each query charged against that balance.

## Setup and configuration

Claude Web and Claude Desktop can connect through Claude’s custom connector settings. Cursor and VS Code have installation links in the repository that add the remote HTTP server configuration. Other clients can use the same endpoint if they support MCP over HTTP.

The connection URL is:

```text
https://api.mcp.ai/p_contas_cpfl_download_ocr
```

No environment variables or local service credentials are specified in the provided setup material. Authentication uses the service’s magic-link login flow. For client-specific installation steps, consult the repository’s installation documentation.

## Tools and capabilities

The CPFL: Download + OCR server contains one tool:

- `contas_cpfl_download_ocr_consultar`: performs the CPFL: Download + OCR consultation against an official source.

The tool is read-only.

## Limitations and notes

CPFL: Download + OCR is hosted and proprietary, while the public repository is licensed MIT and contains the wrapper materials. This distinction matters if you need to inspect, deploy, or modify the underlying service.

Usage is not described as free or unlimited: each query consumes prepaid credit. Pricing details are maintained separately in the project documentation.

Data returned by the tool is sent to the LLM host selected by the user, such as Claude, ChatGPT, Cursor, or another agent host. The project identifies that host as a subprocesser outside the service’s control and recommends considering plans with training opt-out options. The tool’s read-only design prevents source changes, but it does not eliminate the data-handling considerations of the selected LLM host.

_Full upstream README: https://allmcps.com/mcp/cpfl-download-ocr/readme_