PaddleOCR MCP Server
Provides OCR (Optical Character Recognition) capabilities through MCP, including text extraction and document layout parsing to Markdown. Supports multiple PaddleOCR models like PP-OCRv5, PP-OCRv6, and PP-StructureV3.
README
PaddleOCR MCP Server
Small deployment wrapper for running paddleocr_mcp as a long-lived service on a VPS.
Default setup binds to 127.0.0.1:8000 so the service is not exposed to the public internet. Use SSH tunnel first; Cloudflare Tunnel can be added later.
Requirements
- Linux VPS with
systemd - Python 3.10+
git
Install
sudo git clone <repo-url> /apps/paddleocr-mcp-server
cd /apps/paddleocr-mcp-server
sudo cp .env.example .env
sudo bash scripts/install.sh
sudo systemctl enable --now paddleocr-mcp
Check status:
./scripts/status.sh
Follow logs:
./scripts/logs.sh
Local Access From Laptop
Use SSH tunnel:
ssh -L 8000:127.0.0.1:8000 user@your-vps
Then configure OpenCode with:
{
"mcp": {
"paddleocr": {
"type": "remote",
"url": "http://127.0.0.1:8000/mcp",
"enabled": true,
"timeout": 120000
}
}
}
Configuration
Edit .env:
PADDLEOCR_MCP_MODEL=PP-OCRv5
PADDLEOCR_MCP_PPOCR_SOURCE=local
PADDLEOCR_MCP_HOST=127.0.0.1
PADDLEOCR_MCP_PORT=8000
Useful models:
PP-OCRv5: default text OCR, good starting point.PP-OCRv6: newer text OCR.PP-StructureV3: document layout parsing to Markdown, heavier on CPU.
Restart after config changes:
sudo systemctl restart paddleocr-mcp
Upgrade
cd /apps/paddleocr-mcp-server
sudo git pull
sudo .venv/bin/pip install -r requirements.txt
sudo systemctl restart paddleocr-mcp
Security
Default host is 127.0.0.1. Do not bind to 0.0.0.0 unless you put auth and HTTPS in front of it.
Cloudflare Tunnel + Access can be added later without changing the service.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.