{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_um4jefuf7pes","handle":"page-vision-mcp","url":"https://wellknown.network/agents/page-vision-mcp","links":{"self":"https://wellknown.network/agents/page-vision-mcp/record.json","html":"https://wellknown.network/agents/page-vision-mcp","markdown":"https://wellknown.network/agents/page-vision-mcp/record.md","api":"https://wellknown.network/api/v1/agents/page-vision-mcp","status":"https://wellknown.network/api/v1/agents/page-vision-mcp/status","claim":"https://wellknown.network/agents/page-vision-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/page-vision-mcp/claim.json","badge":"https://wellknown.network/agents/page-vision-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/page-vision-mcp/history","tools":"https://wellknown.network/api/v1/agents/page-vision-mcp/tools"},"ard":{"identifier":"urn:air::server:page-vision-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"page-vision-mcp","summary":"Structured visual analysis pipeline for coding agents - give your AI agent the ability to see","description":"# Page Vision MCP \n \n> Structured visual analysis pipeline for coding agents — give your AI agent the ability to **see**. \n \n[![PyPI](https://img.shields.io/pypi/v/page-vision-mcp.svg)](https://pypi.org/project/page-vision-mcp/) \n[![Python](https://img.shields.io/pypi/pyversions/page-vision-mcp.svg)](https://pypi.org/project/page-vision-mcp/) \n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) \n \n## What It Does \n \nPage Vision MCP turns visual analysis from a prompt into a **tool**. Instead of asking an LLM to \"look at this image,\" your coding agent calls a structured API that returns consistent, machine-readable results with coordinates. \n \n**5 Tools:** \n \n| Tool | What It Does | VLM | Playwright | \n|------|-------------|:---:|:----------:| \n| `capture_page` | Screenshot a webpage (fallback) | - | Yes | \n| `analyze_ui` | Structured UI analysis with region-level localization | Yes | - | \n| `compare_ui` | Screenshot diff with mode constraints | Yes | - | \n| `extract_text` | Block-level OCR with coordinates | Yes | - | \n| `crop_analyze` | Progressive crop refinement with depth guards | Yes | - | \n \n**3 Resources:** `vision://health` | `vision://version` | `vision://models` \n \n## Pipeline \n \n``` \nScreenshot ──> analyze_ui ──> Structured JSON \n                  │ \n                  ├── Need detail? ──> crop_analyze (depth +1) \n                  ├── Need text?   ──> extract_text \n                  └── Need diff?   ──> compare_ui \n``` \n \n## Quick Start \n \n### Install \n \n```bash \npip install page-vision-mcp \n \n# Optional: Playwright for screenshot fallback \npip install \"page-vision-mcp[playwright]\" \nplaywright install chromium \n``` \n \n### Configure \n \nSet environment variables (or create a `.env` file, see `.env.example`): \n \n```bash \nVISION_API_KEY=your-api-key \nVISION_BASE_URL=https://api.openai.com/v1 \nVISION_MODEL_ID=gpt-4o \n``` \n \nWorks with any OpenAI-compatible VLM: GPT-4o, GLM-4V, Qwen-VL, etc. \n \n### MCP Cl…","publisher":{"name":"666666999999666","url":null},"homepage":"https://github.com/666666999999666/page-vision-mcp","repository":"https://github.com/666666999999666/page-vision-mcp","version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp","vision","ui-analysis","ocr","screenshot","coding-agent","vlm"],"pricing":null,"endpoints":[{"url":"pypi:page-vision-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"code.generation","name":"Code Generation","confidence":1,"provenance":"derived"},{"slug":"media.image-understanding","name":"Image Understanding","confidence":1,"provenance":"declared"},{"slug":"documents.ocr","name":"OCR","confidence":1,"provenance":"declared"}],"categories":["code","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":"page-vision-mcp","registry":"pypi","observedAt":"2026-10-22T17:24:46.565Z","publishedAt":"2026-07-17T08:38:11.159984Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"page-vision-mcp","url":"https://pypi.org/project/page-vision-mcp/","firstSeenAt":"2026-09-10T09:25:22.982Z","fetchedAt":"2026-10-22T17:22:51.381Z","normalizedAt":"2026-10-22T17:22:51.381Z"}]},"firstSeenAt":"2026-09-10T09:25:22.982Z","updatedAt":"2026-10-22T17:24:46.565Z"}