Structured web page representation for AI agents — 97% HTML token reduction
PageMap MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. Structured web page representation for AI agents — 97% HTML token reduction.
PageMap converts raw HTML (100K+ tokens) into structured, AI-readable page maps (2-5K tokens) — a 97% token reduction. It works as an MCP server, Python SDK, and CLI, supporting 16 page types and 30+ e-commerce sites. Agents can read, click, type, and navigate any web page.
Once PageMap is connected, these are the calls the assistant has available:
get_page_map — Start here. Navigate to a URL and get a full structured map with numbered refsexecute_action — Click, type, select, or hover using a ref number from the last get_page_mapfill_form — Fill multiple form fields in one call. More efficient than sequential execute_action callsget_page_state — Check current URL and title without a full rebuild. Use after actions that may navigatescroll_page — Scroll to reveal lazy-loaded content before calling get_page_map againwait_for — Wait for dynamic content to appear (e.g. after a search or form submit)take_screenshot — Capture the visual state when the PageMap alone is ambiguousnavigate_back — Go back one step in browser historyopen_tab — Open a new browser tab and navigate to a URLswitch_tab — Switch to a different open tab by indexlist_tabs — List all open tabs with their URLs and titlesclose_tab — Close a tab by indexBeing a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Among the browser automation options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. PageMap's toolset — get_page_map, execute_action, fill_form and 11 more — is a fair guide to whether it matches your workflow. It is maintained by Retio-ai; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| get_page_map | **Start here.** Navigate to a URL and get a full structured map with numbered refs. |
| execute_action | Click, type, select, or hover using a ref number from the last get_page_map. |
| fill_form | Fill multiple form fields in one call. More efficient than sequential execute_action calls. |
| get_page_state | Check current URL and title without a full rebuild. Use after actions that may navigate. |
| scroll_page | Scroll to reveal lazy-loaded content before calling get_page_map again. |
| wait_for | Wait for dynamic content to appear (e.g. after a search or form submit). |
| take_screenshot | Capture the visual state when the PageMap alone is ambiguous. |
| navigate_back | Go back one step in browser history. |
| open_tab | Open a new browser tab and navigate to a URL. |
| switch_tab | Switch to a different open tab by index. |
| list_tabs | List all open tabs with their URLs and titles. |
| close_tab | Close a tab by index. |
| batch_get_page_map | Fetch multiple URLs in parallel. Use for comparison tasks. |
| Disclaimer | Users are responsible for complying with the terms of service of target websites and all applicable laws when using PageMap. |
{
"mcpServers": {
"pagemap": {
"command": "uvx",
"args": ["ENOENT"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.