Skip to content
MCP server

Suparse Document Processing

Extract structured data from PDFs and documents through the Suparse OCR API

Runs locallyStatus and history
Install
Pricing
Freemium
Platforms
CLI, API
Runs
Locally
Version
1.5.0
Listing updated
2 days ago

About Suparse Document Processing

Suparse Document Processing is a freemium MCP server for files and documents. It runs locally on your machine and is started by your AI client.

The server runs locally over stdio and wraps the Suparse Document Processing API. Your MCP client can point it at a single file or a whole folder, including encrypted PDFs, and ask for results as JSON, CSV, XLSX or Google Sheets. It can let Suparse auto-detect an extraction schema, apply one of your team's templates, or generate a new schema automatically.

Beyond extraction it can split mixed multi-page documents and download or clean up results by document ID. Suparse itself handles invoices, receipts, bank statements, bills of lading and air waybills out of the box, reads tables across pages, and covers handwriting and 100+ languages, according to its website.

The README warns that a connected client can read local document paths and write export files wherever the server process has permission, so it should only be connected to clients and workspaces you trust. It needs Node.js 20+ and a Suparse API key, supplied through SUPARSE_API_KEY or a config file at ~/.config/suparse/config.json.

Install

Run in a terminal

claude mcp add suparse-mcp --env SUPARSE_API_KEY='<SUPARSE_API_KEY>' -- npx -y @suparse/mcp

Add to claude_desktop_config.json

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

Add to ~/.cursor/mcp.json

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

Add to .vscode/mcp.json

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

Add to ~/.codeium/windsurf/mcp_config.json

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

Add to your client's MCP settings (most use this shape)

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

Configuration

  • SUPARSE_API_KEYSuparse API key used to authenticate requests.Required

What it does

Single file or folder input
Process one document or an entire folder, including encrypted PDFs.
Multiple export formats
Send extracted data to JSON, CSV, XLSX or Google Sheets.
Schema auto-detection
Let Suparse pick a schema, or apply your team's templates.
Automatic schema creation
Generate a new extraction schema from a sample document.
Split mixed documents
Separate multi-page files that bundle several documents.
Result cleanup by ID
Download or remove processed results by document ID.

Good for

  • Turn a folder of supplier invoices into one spreadsheet
  • Extract line items from bank statements for bookkeeping
  • Pull fields from shipping documents such as bills of lading
  • Split a scanned bundle into individual documents and extract each

Pricing

Freemium

50 free pages to start; paid Standard, Business and Enterprise plans, prices not published

Prices change. Check suparse.com before you buy.

Suparse Document Processing FAQ

What do I need to run it?

Node.js 20 or newer and a Suparse API key, set as SUPARSE_API_KEY or stored in ~/.config/suparse/config.json.

Does it run locally or remotely?

It is a local stdio server launched with npx -y @suparse/mcp, which calls the Suparse API.

Which clients are covered in the README?

Claude Code, Claude Desktop, Codex, Cursor, VS Code with GitHub Copilot, Gemini CLI and Windsurf.

Is there a free allowance?

Suparse's website says you can start with 50 free pages.

Is Suparse Document Processing free?

Suparse Document Processing has a free plan, with paid plans for more usage or features.

How do I add Suparse Document Processing to Claude Code?

Run this command in your terminal: claude mcp add suparse-mcp --env SUPARSE_API_KEY='<SUPARSE_API_KEY>' -- npx -y @suparse/mcp

What are the best alternatives to Suparse Document Processing?

The closest alternatives to Suparse Document Processing are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Suparse Document Processing

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools