A Model Context Protocol server providing OCR capabilities for images and videos using GLM-4.1V-Thinking-Flash
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-server-ocr","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# MCP OCR Server A Model Context Protocol (MCP) server that provides OCR (Optical Character Recognition) capabilities for images and videos using GLM-4.1V-Thinking-Flash. ## Features - **Image OCR**: Extract text from images using GLM-4.1V-Thinking-Flash - **Video OCR**: Extract text from video frames (planned feature) - **Custom Prompts**: Support for custom OCR prompts - **MCP Integration**: Full MCP protocol support for seamless integration ## Requirements - Python 3.10+ - GLM-4.1V-Thinking-Flash API key from ZhipuAI ## Quick Start with uvx The fastest way to get started is using `uvx`: ```bash # Install and run directly uvx mcp-server-ocr # Or install for development uvx --python 3.10 --with-editable . mcp-server-ocr ``` ## Installation ### Using uv (recommended) ```bash # Clone the repository git clone <repository-url> cd ocr # Install dependencies uv sync # Run the server uv run mcp-server-ocr ``` ### Using pip ```bash # Clone the repository git clone <repository-url> cd ocr # Install dependencies pip install -e . # Run the server mcp-server-ocr ``` ## Configuration Set your GLM-4.1V-Thinking-Flash API key as an environment variable: ```bash export ZHIPU_API_KEY="your-api-key-here" ``` ## Usage ### Available Tools 1. **ocr_image**: Perform OCR on image files - `image_path`: Path to the image file - `prompt`: Custom prompt for OCR processing (optional) 2. **ocr_video**: Perform OCR on video frames (coming soon) - `video_path`: Path to the video file - `prompt`: Custom prompt for video OCR processing (optional) - `frame_interval`: Extract frames every N seconds (optional) ### Available Prompts 1. **ocr_image**: Extract text from an image 2. **ocr_video**: Extract text from video frames ## Build and Publish ### Build the package ```bash # Using uv uv build # Using pip python -m build ``` ### Publish to PyPI ```bash # Using uv uv publish # Using twine twine upload dist/* ``` ## Development ### Setup development e…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.