{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_93te4cfy6zhx","handle":"vision-mcp-2","url":"https://wellknown.network/agents/vision-mcp-2","links":{"self":"https://wellknown.network/agents/vision-mcp-2/record.json","html":"https://wellknown.network/agents/vision-mcp-2","markdown":"https://wellknown.network/agents/vision-mcp-2/record.md","api":"https://wellknown.network/api/v1/agents/vision-mcp-2","status":"https://wellknown.network/api/v1/agents/vision-mcp-2/status","claim":"https://wellknown.network/agents/vision-mcp-2/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/vision-mcp-2/claim.json","badge":"https://wellknown.network/agents/vision-mcp-2/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/vision-mcp-2/history","tools":"https://wellknown.network/api/v1/agents/vision-mcp-2/tools"},"ard":{"identifier":"urn:air::server:vision-mcp-2","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"vision-mcp","summary":"MCP server for image analysis using Vision Language Models","description":"# Vision MCP\n\nMCP server for image analysis using Vision Language Models.\n\n## Quickstart\n\n1. Install `uv` (Python package manager):\n   ```sh\n   curl -LsSf https://astral.sh/uv/install.sh | sh\n   ```\n\n2. Configure your MCP client (e.g., Claude Desktop):\n\nGo to `Claude > Settings > Developer > Edit Config > claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"Vision\": {\n      \"command\": \"uvx\",\n      \"args\": [\"vision-mcp\"],\n      \"env\": {\n        \"OPENAI_API_KEY\": \"your-api-key\",\n        \"OPENAI_API_BASE\": \"https://api.openai.com\",\n        \"OPENAI_MODEL\": \"gpt-4o\"\n      }\n    }\n  }\n}\n```\n\n## Environment Variables\n\n| Variable | Required | Description |\n|----------|----------|-------------|\n| `OPENAI_API_KEY` | Yes | API key for authentication |\n| `OPENAI_API_BASE` | Yes | API base URL |\n| `OPENAI_MODEL` | Yes | Model name for vision tasks |\n\n## Available Tools\n\n| Tool | Description |\n|------|-------------|\n| `analyze_image` | Analyze images using Vision Language Model |\n\n### analyze_image\n\nAnalyze and understand image content from files or URLs.\n\n**Parameters:**\n- `prompt` (str): The text prompt describing what to analyze\n- `image_source` (str): Image URL or local file path\n\n**Supported formats:** JPEG, PNG, WebP\n\n## License\n\nMIT\n\n## Acknowledgments\n\nThis project is inspired by [MiniMax-Coding-Plan-MCP](https://github.com/MiniMax-AI/MiniMax-Coding-Plan-MCP) by MiniMax AI.","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp","vision","image-analysis"],"pricing":null,"endpoints":[{"url":"pypi:vision-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"media.image-understanding","name":"Image Understanding","confidence":1,"provenance":"declared"}],"categories":["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":"vision-mcp","registry":"pypi","observedAt":"2026-10-22T23:26:16.680Z","publishedAt":"2025-12-22T05:17:03.906943Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"vision-mcp","url":"https://pypi.org/project/vision-mcp/","firstSeenAt":"2026-09-10T15:23:41.923Z","fetchedAt":"2026-10-22T23:24:42.904Z","normalizedAt":"2026-10-22T23:24:42.904Z"}]},"firstSeenAt":"2026-09-10T15:23:41.923Z","updatedAt":"2026-10-22T23:26:16.680Z"}