{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_rd8na8w958um","handle":"vlm-mcp","url":"https://wellknown.network/agents/vlm-mcp","links":{"self":"https://wellknown.network/agents/vlm-mcp/record.json","html":"https://wellknown.network/agents/vlm-mcp","markdown":"https://wellknown.network/agents/vlm-mcp/record.md","api":"https://wellknown.network/api/v1/agents/vlm-mcp","status":"https://wellknown.network/api/v1/agents/vlm-mcp/status","claim":"https://wellknown.network/agents/vlm-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/vlm-mcp/claim.json","badge":"https://wellknown.network/agents/vlm-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/vlm-mcp/history","tools":"https://wellknown.network/api/v1/agents/vlm-mcp/tools"},"ard":{"identifier":"urn:air::server:vlm-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"vlm-mcp","summary":"VLM Image Understanding MCP Server - Support OpenAI protocol compatible VLMs","description":"# VLM MCP Server\n\n[中文版本](./README_zh.md)\n\n## Why This Project?\n\nWhen using Claude Code with third-party models, they are typically text-only models without image processing capabilities. Adding an MCP server with image processing capability is essential for tasks that require visual understanding.\n\nThis project enables users to select their own Vision-Language Model (VLM) for image processing.\n\n## Features\n\n- **extract_text_from_image**: Extract text from images (OCR)\n- **ui_to_artifact**: Convert UI screenshots to code, prompts, design specs, or descriptions\n- **extract_text_from_screenshot**: Extract text from screenshots with code recognition support\n- **diagnose_error_screenshot**: Analyze error screenshots and diagnose issues\n- **understand_technical_diagram**: Analyze technical diagrams (architecture, flowcharts, UML, etc.)\n- **analyze_data_visualization**: Analyze data visualization charts\n- **ui_diff_check**: UI comparison to detect visual differences\n- **analyze_image**: General-purpose image analysis\n\n## Environment Variables\n\n| Variable | Required | Description |\n|----------|----------|-------------|\n| `VLM_API_KEY` | Yes | API key |\n| `VLM_BASE_URL` | No | Custom API endpoint (default: https://api.openai.com/v1) |\n| `VLM_MODEL` | No | Model to use (default: gpt-4o) |\n| `VLM_MAX_IMAGE_SIZE` | No | Maximum image size (default: 3MB). Images exceeding this size will be automatically compressed before processing. Supported formats: `3MB`, `3M`, `3145728` (bytes), `1024KB`, etc. |\n\n## Quick Start\n\n### Using uvx (Recommended)\n\n```bash\n# Copy config template and fill in your API Key\ncp .env.example .env\n# Edit .env file and fill in VLM_API_KEY\n\n# Run directly (will automatically load .env file)\nuvx vlm-mcp\n```\n\n### Using pip\n\n```bash\n# Install\npip install vlm-mcp\n\n# Or install in development mode\npip install -e .\n```\n\n### Configure Environment Variables\n\n```bash\n# OpenAI\nexport VLM_API_KEY=sk-xxx\nexport VLM_MODEL=gpt-4o\n\n# Custom API (e.g., Ollama)\nexport VLM_A…","publisher":null,"homepage":"https://github.com/example/vlm-mcp","repository":"https://github.com/example/vlm-mcp","version":"0.2.0","license":"MIT","protocols":["mcp"],"tags":["ai","image","mcp","ocr","vision","vlm"],"pricing":null,"endpoints":[{"url":"pypi:vlm-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"media.image-understanding","name":"Image Understanding","confidence":1,"provenance":"declared"},{"slug":"documents.ocr","name":"OCR","confidence":1,"provenance":"declared"},{"slug":"analytics.reporting","name":"Reporting & Dashboards","confidence":0.836,"provenance":"derived"}],"categories":["analytics","documents","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":"vlm-mcp","registry":"pypi","observedAt":"2026-10-22T23:26:19.275Z","publishedAt":"2026-03-11T09:06:57.706056Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"vlm-mcp","url":"https://pypi.org/project/vlm-mcp/","firstSeenAt":"2026-09-10T15:23:47.746Z","fetchedAt":"2026-10-22T23:24:48.560Z","normalizedAt":"2026-10-22T23:24:48.560Z"}]},"firstSeenAt":"2026-09-10T15:23:47.746Z","updatedAt":"2026-10-22T23:26:19.275Z"}