{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_kpp2gfmmshyg","handle":"mcp-vision-recognition","url":"https://wellknown.network/agents/mcp-vision-recognition","links":{"self":"https://wellknown.network/agents/mcp-vision-recognition/record.json","html":"https://wellknown.network/agents/mcp-vision-recognition","markdown":"https://wellknown.network/agents/mcp-vision-recognition/record.md","api":"https://wellknown.network/api/v1/agents/mcp-vision-recognition","status":"https://wellknown.network/api/v1/agents/mcp-vision-recognition/status","claim":"https://wellknown.network/agents/mcp-vision-recognition/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-vision-recognition/claim.json","badge":"https://wellknown.network/agents/mcp-vision-recognition/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-vision-recognition/history","tools":"https://wellknown.network/api/v1/agents/mcp-vision-recognition/tools"},"ard":{"identifier":"urn:air::server:mcp-vision-recognition","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-vision-recognition","summary":"MCP server for image recognition using Anthropic and OpenAI vision APIs","description":"# MCP Image Recognition Server\n\nAn MCP server that provides image recognition capabilities using Anthropic and OpenAI vision APIs. Version 0.1.2.\n\n## Features\n\n- Image description using Anthropic Claude Vision or OpenAI GPT-4 Vision\n- Support for multiple image formats (JPEG, PNG, GIF, WebP)\n- Configurable primary and fallback providers\n- Base64 and file-based image input support\n- Optional text extraction using Tesseract OCR\n\n## Requirements\n\n- Python 3.8 or higher\n- Tesseract OCR (optional) - Required for text extraction feature\n  - Windows: Download and install from [UB-Mannheim/tesseract](https://github.com/UB-Mannheim/tesseract/wiki)\n  - Linux: `sudo apt-get install tesseract-ocr`\n  - macOS: `brew install tesseract`\n\n## Installation\n\n1. Clone the repository:\n```bash\ngit clone https://github.com/mario-andreschak/mcp-image-recognition.git\ncd mcp-image-recognition\n```\n\n2. Create and configure your environment file:\n```bash\ncp .env.example .env\n# Edit .env with your API keys and preferences\n```\n\n3. Build the project:\n```bash\nbuild.bat\n```\n\n## Usage\n\n### Running the Server\nSpawn the server using python:\n```bash\npython -m mcp_vision_recognition.server\n```\n\nStart the server using batch instead:\n```bash\nrun.bat server\n```\n\nStart the server in development mode with the MCP Inspector:\n```bash\nrun.bat debug\n```\n\n### Available Tools\n\n1. `describe_image`\n   - Input: Base64-encoded image data and MIME type\n   - Output: Detailed description of the image\n\n2. `describe_image_from_file`\n   - Input: Path to an image file\n   - Output: Detailed description of the image\n\n### Environment Configuration\n\n- `ANTHROPIC_API_KEY`: Your Anthropic API key.\n- `OPENAI_API_KEY`: Your OpenAI API key.\n- `VISION_PROVIDER`: Primary vision provider (`anthropic` or `openai`).\n- `FALLBACK_PROVIDER`: Optional fallback provider.\n- `LOG_LEVEL`: Logging level (DEBUG, INFO, WARNING, ERROR).\n- `MAX_TOKENS`: Maximum number of tokens generated in a vision response (default: `1024`).\n- `ENABLE_OCR`: Enable Te…","publisher":{"name":"Mario","url":null},"homepage":null,"repository":null,"version":"0.1.3","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:mcp-vision-recognition","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"media.image-understanding","name":"Image Understanding","confidence":1,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"}],"categories":["dev","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-vision-recognition","registry":"pypi","observedAt":"2026-10-22T12:27:00.681Z","publishedAt":"2026-08-08T02:42:29.379414Z","latestVersion":"0.1.3"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-vision-recognition","url":"https://pypi.org/project/mcp-vision-recognition/","firstSeenAt":"2026-09-10T05:21:49.911Z","fetchedAt":"2026-10-22T12:25:39.503Z","normalizedAt":"2026-10-22T12:25:39.503Z"}]},"firstSeenAt":"2026-09-10T05:21:49.911Z","updatedAt":"2026-10-22T12:27:00.681Z"}