Rossum MCP Server Documentation

Getting Started:

• Installation
  • Prerequisites
  • Installation Methods
  • Environment Variables
• Usage
  • Running the MCP Server
  • Using with MCP Clients
  • Using with Smolagents
  • Available Tools
• Annotation Status Workflow
  • Annotation States
  • Important Considerations
  • Example Workflows
  • Error Handling

Reference:

• API Reference
  • RossumMCPServer
• MCP to Rossum SDK Mapping
  • Overview
  • Tool-to-SDK Mapping
  • Async Wrapper Pattern
  • Rossum API Resources
  • Authentication
  • Error Handling

Examples:

• Examples
  • Available Examples
  • Building Your Own Agents
  • Next Steps

Welcome to Rossum MCP Server

A Model Context Protocol (MCP) server that provides tools for uploading documents and retrieving annotations using the Rossum API. Built with Python and the official rossum-sdk.

Features

MCP Tools:

• upload_document: Upload a document to Rossum for processing

• get_annotation: Retrieve annotation data for a previously uploaded document

• list_annotations: List all annotations for a queue with optional filtering

• get_queue: Retrieve queue details including schema_id

• get_schema: Retrieve schema details and content

• get_queue_schema: Retrieve complete schema for a queue in a single call

Examples and Extensions

The documentation includes examples demonstrating how to build downstream tools that work with Rossum data:

• Plotting tool for data visualization (bar, line, pie, scatter, heatmap charts)

• Integration patterns for AI agents (smolagents)

• Templates for building custom processing tools

• See the Examples section for details

Quick Start

Install the package with documentation dependencies:

pip install -e ".[docs]"

Run the MCP server:

python -m rossum_mcp.server

Indices and tables

• Index

• Module Index

• Search Page