Suparse MCP Server

@suparse

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

suparse

投稿者

Michael

Suparse MCP Server について

Extract structured data from PDFs and documents with Suparse AI OCR.

#ocr #document-processing #pdf #data-extraction #ai #llm #structured-data

Suparse 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": {
    "suparse": {
      "command": "npx",
      "args": [
        "-y",
        "@suparse/mcp"
      ],
      "env": {
        "SUPARSE_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Suparse MCP Server のツール

Process one local document through Suparse. Defaults to result_mode defer, which uploads and polls only, then returns compact task_id/document_ids for later download_results. Use result_mode return_json only when you need the full JSON extraction in the MCP response. cleanup is only valid with return_json.

Process all supported files in an immediate local folder through Suparse. Defaults to result_mode defer, which uploads and polls only, then returns compact task_id/document_ids for later download_results. Use result_mode return_json only when you need full JSON extractions in the MCP response. cleanup is only valid with return_json.

List extraction templates for choosing an extraction template. Agents must use team_templates for processing. System templates are discovery-only in MCP: if a matching system template exists but no matching team template exists, ask the user to add that system template to their templates in the Suparse UI before processing. If no matching team or system template exists, ask the user to create a custom extraction schema for that document type in the Suparse UI.

Fetch JSON extraction results for one or more Suparse document IDs directly in the MCP response. This can be large; use only when you need the full JSON in context. For CSV, XLSX, Google Sheets, or saved JSON files, use download_results. If you need cleanup after fetching, call delete_documents after this tool succeeds.

Fetch an export for one or more Suparse document IDs and write it directly to local disk. Use this for CSV, XLSX, Google Sheets, and saved JSON files. Do not call fetch_json_results unless you intentionally need full JSON in the MCP response. If output_path is a directory, the API-provided filename is used inside that directory. If cleanup is needed, call delete_documents after this tool succeeds.

Delete one or more documents from Suparse by document ID.

概要

What is Suparse?

Suparse MCP Server is a Model Context Protocol connector for the Suparse Document Processing API, enabling AI assistants to extract structured data from local PDFs and images without writing upload, polling, or export code.

How to use Suparse?

Install it with npx, create a Suparse API key, configure an MCP-compatible client with SUPARSE_API_KEY, restart the client, and ask your assistant to process local documents.

Key features of Suparse

AI-powered extraction from invoices, receipts, bank statements, purchase orders, and other supported document types.
Batch processing for local folders of supported documents.
Template listing so assistants can choose the right extraction schema.
Result downloads as JSON, CSV, XLSX, or Google Sheets.
Document cleanup support for privacy-sensitive workflows.
Integration with Claude Code, Claude Desktop, Codex, and other MCP-compatible clients.

Use cases of Suparse

Extracting totals, line items, vendor details, and dates from invoices or receipts inside an AI assistant workflow.
Processing folders of financial, logistics, HR, healthcare, or business documents without building a custom parser.
Exporting structured document data to spreadsheets for accounting, operations, or review workflows.
Letting AI coding assistants use Suparse templates and extraction results while working on local files.
Cleaning up processed documents after downloading results for privacy-conscious document workflows.

よくある質問

How do I get a Suparse API key?

Sign in at [suparse.com](https://suparse.com), open the **API Keys** tab, generate a new key, and copy it securely because the key value is shown only once.

What clients can use Suparse MCP Server?

Suparse MCP Server works with MCP-compatible local clients, including Claude Code, Claude Desktop, Codex, and other assistants that support Model Context Protocol servers.

What file types can Suparse process through MCP?

Suparse can process supported local PDFs and images, including common document workflows for invoices, receipts, bank statements, purchase orders, and other business documents.

Can Suparse MCP Server export results?

Yes, assistants can download extraction results as JSON, CSV, XLSX, or Google Sheets when supported by the account workflow.

Can processed documents be deleted after extraction?

Yes, ask the assistant to download the result first and then delete the processed document from Suparse when cleanup is required.

What should I do if Suparse tools do not appear in my assistant?

Restart the MCP client after editing its configuration, confirm Node.js 20 or newer is installed, and verify that `SUPARSE_API_KEY` is set correctly.

「その他」の他のコンテンツ

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.

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

Soar Flight Booking MCP

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.

MCP Toolbox for Databases

googleapis

MCP Toolbox for Databases is an open source MCP server for databases.

15.9K