MCP-VizAPI: Visual Data Extraction with VizAPI.ai

Name: MCP-VizAPI: Visual Data Extraction with VizAPI.ai
Author: IvanZidov

@IvanZidov

リポジトリ

MCP-VizAPI: Visual Data Extraction with VizAPI.ai について

概要はまだありません

#vizapi #data-extraction #mcp-server

基本情報

カテゴリ

データと分析

ライセンス

MIT license

ランタイム

python

トランスポート

stdio

公開者

IvanZidov

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": {
    "vizapi-mcp-server": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "-e",
        "."
      ]
    }
  }
}

ツール

ツールは検出されませんでした

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 MCP-VizAPI: Visual Data Extraction with VizAPI.ai?

MCP-VizAPI: Visual Data Extraction with VizAPI.ai is an MCP server that integrates with VizAPI.ai to enable AI agents to extract structured data from images and documents. It is designed for developers and users of MCP-compatible clients who need automated visual data extraction via predefined templates or field suggestions.

How to use MCP-VizAPI: Visual Data Extraction with VizAPI.ai?

Install with uv (Python 3.12+ required) by cloning the repo and running uv pip install -e ., or use Docker (docker build -t mcp/vizapi --build-arg PORT=8060 .). Configure a .env file with VIZAPI_API_KEY and select transport (TRANSPORT=sse or TRANSPORT=stdio). Run via uv run src/main.py or docker run --env-file .env -p 8060:8060 mcp/vizapi. Connect your MCP client (e.g., Claude Desktop, Windsurf) using the provided SSE URL or stdio command.

Key features of MCP-VizAPI: Visual Data Extraction with VizAPI.ai

List all private extraction templates for the authenticated user.
Retrieve a specific extraction template by its ID.
Analyze a document or image to suggest extraction fields.
Extract structured data using a predefined template.
Check the operational health of the VizAPI.ai service.

Use cases of MCP-VizAPI: Visual Data Extraction with VizAPI.ai

Automating invoice or receipt data extraction from scanned images.
Extracting structured information from business documents using custom templates.
Integrating visual data extraction into AI agent workflows (e.g., Claude Desktop, n8n).
Prototyping extraction pipelines by suggesting fields for new document types.

FAQ from MCP-VizAPI: Visual Data Extraction with VizAPI.ai

What prerequisites are needed to run the server?

Python 3.12+ and a VizAPI.ai account with a valid API key are required. Docker is recommended for containerized deployment.

How do I get a VizAPI API key?

Obtain your API key from the VizAPI dashboard at https://app.vizapi.ai/dashboard. Set it as VIZAPI_API_KEY in your .env file.

What transport protocols are supported?

The server supports both Server-Sent Events (SSE) and Standard I/O (stdio) transports, configurable via the TRANSPORT environment variable.

Can I run the server without Docker?

Yes. Install dependencies with uv and run uv run src/main.py directly. Ensure VIZAPI_API_KEY is set in your .env file.

How do I configure the server for SSE transport?

Set TRANSPORT=sse in your .env file, optionally adjust HOST and PORT (default 8060), and start the server. Connect your MCP client to http://<host>:<port>/sse.