DataHub MCP Server

@noreuzis

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

noreuzis

DataHub MCP Server について

DataHub MCP Server implementation with FastMCP 2.6.0

#mcp-datahub#datahub#mcp-server

DataHub MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-datahub": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

DataHub MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is DataHub MCP Server?

A Model Context Protocol server implementation that exposes DataHub API endpoints as tools for MCP clients. Built with FastMCP 2.6.0, it provides secure, configurable access to DataHub data services including person, company, vehicle, process, and market data lookups. Designed for developers integrating DataHub data into MCP-compatible applications.

How to use DataHub MCP Server?

Install via pip in a Python 3.8+ virtual environment, then run from the command line. Two transports are supported: stdio and SSE (default). For example, python -m src.fastmcp_server.server --transport sse --port 8000. Enable authentication with the --auth flag. Configuration is done via a JSON file or command-line arguments; available tools include over 20 DataHub API endpoints covering person, company, vehicle, process, Infobip, and market data.

Key features of DataHub MCP Server

Exposes all DataHub API endpoints as MCP tools
Supports stdio and SSE transport modes
Optional bearer token authentication with RSA key pairs
JSON-based configuration with sensible defaults
Robust error handling and detailed logging
Type safety with complete annotations

Use cases of DataHub MCP Server

Retrieve person information by CPF, email, name, phone, or LinkedIn URL
Look up company data by CNPJ or validate company information
Get vehicle details by license plate, including FIPE valuation
Query legal process information by process number
Validate CPF and phone number combinations via Infobip

よくある質問

What DataHub API endpoints are exposed?

The server exposes tools for person data (get_person_by_cpf, validate_person, etc.), company data (get_company_by_cnpj, validate_company), vehicle data (get_vehicle_webhook_plate, get_vehicle_fipe_plate), process data (get_process_by_number), Infobip services (validate_cpf_phonenumber), and market data (get_market_cep).

What are the runtime requirements?

Python 3.8 or higher and a virtual environment are recommended. The package depends on FastMCP 2.6.0 and other standard libraries.

How is authentication handled?

Optional bearer token authentication is available using the `--auth` flag. When enabled, the server generates an access token (default 1-hour expiration) and displays it at startup. CORS origins can be restricted in configuration.

What transport modes are available?

The server supports both stdio and SSE (Server-Sent Events) transports. SSE is the default and can be configured with a host and port. stdio is used for direct integration with clients that support it.

How can I discover available tools while the server is running?

Use the included `tools_discovery.py` script (e.g., `python tools_discovery.py --url http://127.0.0.1:8000`) to list all tools and save them to `tool_info.json`.

「その他」の他のコンテンツ

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.