# Reclame Aqui [Health: Active]

**Category:** 🎧 Support & Service Management  
**Repository:** https://github.com/mcp-dir/reclameaqui-mcp  
**GitHub Stars:** 0  
**Views:** 1  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/reclame-aqui

## Description
Manage your company's complaints on Reclame Aqui through the Company Area account. You provide the c

## Tools
Capabilities this server exposes over MCP:

- **reclameaqui_listar_reclamacoes** — Lista as reclamações da sua empresa no Reclame Aqui (mais recentes primeiro). Traz id, título, status, consumidor, cidade/UF, se já foi respondida e avaliação.
- **reclameaqui_reclamacao** — Detalhe de uma ou mais reclamações por id (conversa completa em treatments, avaliação, score, status). Aceita lista de ids.
- **reclameaqui_responder** — Responde uma reclamação da sua empresa no Reclame Aqui. Por padrão é resposta PÚBLICA; use privada=true para mensagem interna ao consumidor. AÇÃO PÚBLICA — confirme o texto antes de enviar.

Bulk support: accepts ids for batched execution.
- **reclameaqui_reputacao** — Indicadores de reputação da sua empresa no Reclame Aqui (nota/rating e principais problemas reclamados).
- **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": {
  "reclame-aqui": {
    "url": "https://api.mcp.ai/p_reclameaqui"
  }
}
```

## Documentation

## What Reclame Aqui does

The Reclame Aqui MCP server gives AI agents access to complaint data associated with a company account in Reclame Aqui’s Company Area. It uses the same web area that account holders access rather than the paid Reclame Aqui API.

The available tools cover four workflows:

- `reclameaqui_listar_reclamacoes` lists the company’s complaints, with newer items first.
- `reclameaqui_reclamacao` retrieves one or more complaints by ID, including the conversation in `treatments`, evaluation, score, and status.
- `reclameaqui_responder` is documented as replying to a company complaint.
- `reclameaqui_reputacao` returns reputation indicators, including rating and commonly reported problems.

Typical prompts include finding unanswered complaints, opening the latest complaint, or checking the company’s current reputation.

## How it works

The hosted endpoint is available at `https://api.mcp.ai/p_reclameaqui` and communicates over MCP over HTTP. Any MCP client with HTTP support can connect to that URL. The README specifically lists Claude Desktop, Cursor, VS Code, Cline, and Continue, and also mentions compatibility with ChatGPT, Manus, OpenClaw, and other MCP clients.

Authentication is tied to the company’s Reclame Aqui account in the Company Area. The README’s main description refers to providing the company username and password, while its installation notes advertise a passwordless magic-link login. Treat the exact sign-in flow as something to confirm with the current hosted service.

## Setup and configuration

For Claude, the documented custom connector URL is `https://api.mcp.ai/p_reclameaqui`. Cursor and VS Code have installation links that configure the same endpoint. Other clients should use their MCP-over-HTTP setup and enter the endpoint directly.

The repository is a public wrapper containing manifests, documentation, and agent skills; the hosted MCP service itself is proprietary.

## Limitations and notes

The Reclame Aqui MCP server is a hosted service, so using it requires a client that supports MCP over HTTP and access to the remote endpoint.

One section labels the integration as read-only and says that no source data is changed, while the tool list includes `reclameaqui_responder`, which is described as sending a reply. Confirm whether response actions are enabled for your account and deployment before relying on the server for write operations.

Returned data is sent to the selected LLM host, such as Claude, ChatGPT, Cursor, or another agent host. The documentation identifies Reclame Aqui and the chosen LLM host as subprocessors and recommends considering plans with training opt-out options. Review the provider’s privacy and LGPD documentation before sending complaint information.

The repository is licensed under MIT, but the hosted server is described separately as proprietary.

_Full upstream README: https://allmcps.com/mcp/reclame-aqui/readme_