mcp-bigdatacorp

Name: mcp-bigdatacorp
Author: codespar

Local

github.com/codesparBusiness & Marketing275Updated 4w ago

Repository

About mcp-bigdatacorp

mcp-bigdatacorp is an MCP server for BigDataCorp, a Brazilian data enrichment and KYC platform covering CPF, CNPJ, vehicle, property and antifraud datasets. It is aimed at Brazilian e-commerce and lending workflows that need identity checks, AML screening and fraud scoring.

Key features

01CPF person data lookup
02CNPJ company data lookup
03Vehicle and property data lookup
04Sanctions and PEP screening
05Composite antifraud score
06CORREIOS and IBGE address validation

Use cases

01KYC verification for Brazilian e-commerce or lending
02AML and sanctions list screening
03Fraud risk assessment before approving an order or loan

MCP support

This project is an MCP server that exposes BigDataCorp dataset lookups and antifraud scoring as tools for MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config

{
  "mcpServers": {
    "codespar-mcp-bigdatacorp": {
      "command": "npx",
      "args": [
        "-y",
        "@codespar/mcp-bigdatacorp"
      ],
      "env": {
        "BIGDATACORP_ACCESS_TOKEN": "<BIGDATACORP_ACCESS_TOKEN>",
        "BIGDATACORP_TOKEN_ID": "<BIGDATACORP_TOKEN_ID>",
        "BIGDATACORP_API_BASE": "<BIGDATACORP_API_BASE>"
      }
    }
  }
}

Run commandnpx -y @codespar/mcp-bigdatacorp

Environment variables to set

BIGDATACORP_ACCESS_TOKENSecretAccessToken header value from the BigDataCorp dashboard

BIGDATACORP_TOKEN_IDSecretTokenId header paired with the access token

BIGDATACORP_API_BASEAPI base URL — defaults to BigDataCorp production. Override for sandbox.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages

npm@codespar/mcp-bigdatacorp0.1.2stdio

Tools

Saved tool list · updated 2w ago

Parameter	Type	Required	Description
q	string	Yes	Query string — typically 'doc{CPF}'
Datasets	string	Yes	Comma-separated dataset list (e.g. 'basic_data,registration_data,addresses')

Details

From the project README

@codespar/mcp-bigdatacorp

MCP server for BigDataCorp — the Brazilian data-enrichment + KYC platform. CPF / CNPJ / vehicle / property / antifraud datasets used as the standard rail in BR e-commerce + lending agents for KYC, AML, and fraud scoring.

Quick Start

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "bigdatacorp": {
      "command": "npx",
      "args": ["@codespar/mcp-bigdatacorp"],
      "env": {
        "BIGDATACORP_ACCESS_TOKEN": "your-access-token",
        "BIGDATACORP_TOKEN_ID": "your-token-id"
      }
    }
  }
}

Cursor / VS Code

Same config in .cursor/mcp.json.

Tools (10)

Core lookups

Tool	BigDataCorp endpoint	Notes
`persons_lookup`	`POST /v1/datasets/persons`	CPF → name, DOB, mother's name, addresses, contacts, deceased flag
`companies_lookup`	`POST /v1/datasets/companies`	CNPJ → razão social, capital, partners, address, CNAE
`vehicles_lookup`	`POST /v1/datasets/vehicles`	Plate / chassis / RENAVAM → make, model, FIPE, ownership, restrictions
`properties_lookup`	`POST /v1/datasets/properties`	Address or registration → owner history + value estimate

Enrichment slices

Tool	BigDataCorp endpoint	Notes
`financial_data`	`POST /v1/datasets/persons`	Income, score, declared assets, banking, default history
`employment_data`	`POST /v1/datasets/persons`	Current employer, history, monthly income, category
`sanctions_check`	`POST /v1/datasets/persons`	OFAC / UN / EU / BR PEP / CNJ / INSS / IBAMA screening
`social_signals`	`POST /v1/datasets/persons`	Instagram / LinkedIn / Twitter / Facebook presence

Antifraud + address

Tool	BigDataCorp endpoint	Notes
`antifraud_score`	`POST /v1/datasets/antifraud`	Composite fraud score (0-1000) + decision recommendation
`address_validation`	`POST /v1/datasets/addresses`	CORREIOS + IBGE normalization + geocode

Authentication

BigDataCorp uses paired headers (not Bearer):

AccessToken: <BIGDATACORP_ACCESS_TOKEN>
TokenId:     <BIGDATACORP_TOKEN_ID>

Both are required on every request. Issue both credentials from the BigDataCorp platform dashboard:

Platform: https://plataforma.bigdatacorp.com.br

Environment Variables

Variable	Required	Description
`BIGDATACORP_ACCESS_TOKEN`	yes	`AccessToken` header value
`BIGDATACORP_TOKEN_ID`	yes	`TokenId` header value (paired)
`BIGDATACORP_API_BASE`	no	Override base URL (default `https://plataforma.bigdatacorp.com.br`)

BigDataCorp vs Certta vs Caf

Three BR identity rails in this catalog, each with a different specialty:

Provider	Strength	Best for
BigDataCorp	Broad data enrichment + antifraud	KYC + AML + credit decisioning
Certta (`@codespar/mcp-certta`)	KYC + biometrics + ICP-Brasil signature	Onboarding pipelines with signed contracts
Caf (`@codespar/mcp-caf`)	KYC + Trust Platform orchestration	Hosted onboarding flows with policy rules

Enterprise

Need governance, budget limits, and audit trails for agent identity calls? CodeSpar Enterprise adds policy engine, payment routing, and compliance templates on top of these MCP servers.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

Read the getting-started guide

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.