Brazil CNPJ Company Data MCP Server
# Brazil CNPJ Company Data MCP Server
[](https://glama.ai/mcp/servers/mambalabsdev/mcp-brazil-cnpj-company-data) [](https://registry.modelcontextprotocol.io/v0/servers?search=com.mambabuilt/mcp-brazil-cnpj-company-data&limit=1) [](https://www.npmjs.com/package/@mambalabsdev/mcp-brazil-cnpj-company-data) [](https://www.npmjs.com/package/@mambalabsdev/mcp-brazil-cnpj-company-data) [](https://github.com/mambalabsdev/mcp-brazil-cnpj-company-data/blob/main/LICENSE)
An MCP server for the Mamba Labs Brazil CNPJ Company Data actor on Apify. Brazil CNPJ registry data as rows.
## What's Inside
- [What it does](#what-it-does)
- [Quick start](#quick-start)
- [Prerequisites](#prerequisites)
- [Example prompts](#example-prompts)
- [Tool](#tool)
- [Inputs](#inputs)
- [Pricing](#pricing)
- [Full actor documentation](#full-actor-documentation)
- [License](#license)
## What it does
Takes CNPJs and returns one row per company with status, size, capital, CNAE activities, address, phones, Simples and MEI, and tax regime. Partners add one row per partner or administrator.
All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.
## Quick start
You need Node.js 18 or newer and an Apify account with an API token.
Add this to your Claude Desktop config (`claude_desktop_config.json`), Cursor, or any MCP client:
```json
{
"mcpServers": {
"mamba-brazil-cnpj-company-data": {
"command": "npx",
"args": [
"-y",
"@mambalabsdev/mcp-brazil-cnpj-company-data"
],
"env": {
"APIFY_TOKEN": "your-apify-token"
}
}
}
}
```
Restart the client. The `lookup_brazil_cnpj` tool appears.
## Prerequisites
- Node.js 18 or newer.
- An Apify API token from [console.apify.com/account/integrations](https://console.apify.com/account/integrations), set as `APIFY_TOKEN`. The server lists its tool without a token; a call needs one.
## Example prompts
- "Look up CNPJ 07.526.557/0001-00 and list its partners."
- "Is the Brazilian company with CNPJ 33000167000101 active, and what is its main activity?"
## Tool
`lookup_brazil_cnpj`. One tool. Example arguments:
```json
{
"cnpjs": [
"07.526.557/0001-00"
],
"include_partners": true,
"max_partners_per_company": 5
}
```
## Inputs
Every buyer facing input of the actor. Omitted inputs take the actor's own defaults.
| Input | Type | Required | Description |
|---|---|---|---|
| `cnpjs` | array | no | CNPJs to look up, 14 digits with or without punctuation (07.526.557/0001-00 or 07526557000100). An 8 digit root reads the head office. Up to 10,000 per run. In Clay, put the column inside a one item list. |
| `include_partners` | boolean | no | true adds one row per partner or administrator (QSA), charged per partner. Default false. |
| `max_partners_per_company` | number | no | Most partner rows per company, 1 to 1000. Default 100. |
| `dedupe` | boolean | no | true (default) reads a CNPJ once per run even when it appears twice. The repeat is not charged. |
| `max_charge_usd` | number | no | Optional. The run stops before a charge that would pass this amount. Summary rows are always returned. |
## Pricing
Pay per event on Apify, billed to your Apify account. Prices in USD.
| Event | Free plan | Bronze | Silver | Gold |
|---|---|---|---|---|
| `company-row`, one company read from the CNPJ registry | $0.0035 | $0.003325 | $0.00315 | $0.002975 |
| `partner-row`, one partner (QSA) of a company | $0.001 | $0.00095 | $0.0009 | $0.00085 |
| `apify-actor-start`, per run start | $0.005 | $0.005 | $0.005 | $0.005 |
Repeats, CNPJs not found, invalid values, summaries, and refused input are free. Mamba Labs pays the platform costs of the run, Apify proxy traffic included.
## Full actor documentation
[apify.com/mambalabs/brazil-cnpj-company-data](https://apify.com/mambalabs/brazil-cnpj-company-data)
## License
MIT. See [LICENSE](LICENSE).
TDQS
Scored across 1 tool
There is only one tool, so no misselection between tools is possible. Its purpose (CNPJ lookup against Receita Federal open data) is explicitly and narrowly stated.
The single name lookup_brazil_cnpj follows a clean verb_noun snake_case pattern. With only one tool, a consistent convention can be suggested but not demonstrated across the set.
The server is scoped to one narrow operation, but a single tool is thin even for that purpose — no batch lookup, name search, or CNAE query tool accompanies it. Borderline under-provisioned rather than clearly wrong.
The returned payload is very rich (address, CNAE, Simples/MEI, QSA partners), but the surface requires a known CNPJ, so an agent that only has a company name, state, or activity code hits a dead end. Search/filter operations are a notable gap.