rossum-mcp
Verified Safeby stancld
Overview
An MCP (Model Context Protocol) server integrating with the Rossum API to provide AI agents with tools for document processing, queue, schema, engine, automation, and relations management.
Installation
rossum-mcpEnvironment Variables
- ROSSUM_API_TOKEN
- ROSSUM_API_BASE_URL
- ROSSUM_MCP_MODE
- LOG_LEVEL
- REDIS_HOST
- REDIS_PORT
Security Notes
The server runs as a subprocess and relies on environment variables for sensitive data (ROSSUM_API_TOKEN, ROSSUM_API_BASE_URL). This is generally good practice, but the security of these variables depends on the hosting environment. A key security feature is the 'ROSSUM_MCP_MODE' which can be set to 'read-only', disabling all creation, update, and upload operations, significantly reducing the attack surface. There are no obvious signs of 'eval' or other highly dangerous patterns within the MCP server's codebase itself, which contributes to a high security score when properly configured.
Similar Servers
claude-flow
Orchestrates AI agents for Machine Learning Engineering tasks, data processing, feature engineering, and provides a framework for prompt and configuration migration within a Claude-Flow ecosystem.
zen-mcp-server
A server for coordinating and managing AI agents, likely for simulations or complex task execution, leveraging Claude LLMs.
klavis
Creates an AI agent that uses Klavis Strata to interact with Gmail and YouTube through MCP, demonstrating how to summarize a YouTube video and email the summary.
vibe-check-mcp-server
Provides a plug-and-play AI meta-mentor layer for LLM agents, offering metacognitive questioning to prevent over-engineering, reasoning lock-in, and misalignment.