api-server-mcp

Serve document extraction via REST and MCP endpoints using Axum and Tokio.

8.9k|539|Updated Jan 31, 2025
One-click install
npx skills add https://github.com/kreuzberg-dev/kreuzberg --skill api-server-mcp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: api-server-mcp
Source: https://github.com/kreuzberg-dev/kreuzberg/tree/main/.ai-rulez/skills/api-server-mcp
Command: npx skills add https://github.com/kreuzberg-dev/kreuzberg --skill api-server-mcp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a scalable API server to expose document extraction capabilities via REST and MCP, enabling automated processing of diverse documents.

Core Features & Use Cases

  • REST + MCP endpoints: Exposes endpoints for extraction, batch processing, formats, and health checks.
  • Middleware & reliability: Includes CORS, request logging, size limits, and concurrency controls for robust operation.
  • Use Case: Deploy as the backend for AI agents (Claude, etc.) to request on-demand or batch document extraction with embeddings and post-processing.

Quick Start

Run the Axum-based server with the provided environment configuration to start serving extraction requests.

Frequently Asked Questions about api-server-mcp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I expose document extraction to AI agents via an MCP server?

You can expose document extraction to AI agents via an MCP server by deploying this Axum-based API server, which integrates MCP tool endpoints for on-demand and batch document processing across formats like PDF and Office documents.

Can I process batch document extractions using a REST API with Rust?

Yes, you can perform batch document extractions using a Rust REST API. This server handles batch processing requests natively via Axum and Tokio, supporting formats including PDF, images, and Office documents with built-in concurrency controls.

Does this Axum document extraction server support caching and health checks?

Yes, this Axum document extraction server supports both caching and health checks. It includes modular routing, middleware for CORS and request logging, size limits, and configurable environment options to ensure robust enterprise operation.

What is the best way to handle enterprise document processing across multiple file formats?

The best way to handle enterprise document processing is using a scalable API server like this Axum-based solution, which provides single-shot and batch extractions across PDFs, images, and Office documents with configurable middleware and error handling.

How do I set up an Axum and Tokio server for AI agent document extraction workflows?

To set up an Axum and Tokio server for AI agent workflows, you run the provided environment configuration to start serving extraction requests. It exposes REST and MCP endpoints for automated document processing with format detection.

Are there concurrency controls for batch processing PDF and Office documents?

Yes, there are concurrency controls for batch processing PDF and Office documents. The server implements middleware, size limits, and modular error handling to manage concurrent extraction requests reliably.