open-ocr-cli
Agent-first, provider-neutral multimodal OCR CLI for images, PDFs, URLs, JSON schemas, and agentic extraction with Gemini, Kimi, Muse, and OpenRouter.
AI & MLnpx -y open-ocr-cli{
"mcpServers": {
"open-ocr-cli": {
"command": "npx",
"args": [
"-y",
"open-ocr-cli"
]
}
}
}open-ocr-cli is a community MCP server that connects AI assistants like Claude to agent-first, provider-neutral multimodal ocr cli for images, pdfs, urls, json schemas, and agentic extraction with gemini, kimi, muse, and openrouter. It runs locally on your machine, keeping your data private and giving you full control over the connection. AI engineers can use it to chain models and pipelines into more powerful workflows.
About open-ocr-cli
Overview
Agent-first, provider-neutral multimodal OCR CLI for images, PDFs, URLs, JSON schemas, and agentic extraction with Gemini, Kimi, Muse, and OpenRouter.
Links
Topics
ocr, gemini, kimi, muse, openrouter, openai-compatible, cloudflare-ai-gateway, multimodal-ocr, json-schema, structured-output, agentic-ocr, agent-first, coding-agent, mcp-server, cli, command-line-tool, pdf, document-extraction, batch-ocr
Who Should Use open-ocr-cli?
- 1Chain AI models and pipelines through a unified MCP interface
- 2Let Claude orchestrate other AI tools and models
- 3Integrate embeddings, image generation, or speech APIs into your workflow
- 4Build multi-model workflows without writing custom integration code
How to Install open-ocr-cli
Before you start
You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.
- 1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
- 2Paste the install command above and press Enter — Node.js will download and run the server automatically.
- 3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.
The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.