agenteyes-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agenteyes-mcp Take a full-page screenshot of https://example.com and summarize the page."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
agenteyes-mcp
A Node.js MCP server (stdio transport) exposing agent tools backed by headless Chromium. One tool call returns screenshot PNG(s), an accessibility snapshot, and page text — eyes for agents.
Requirements
Node.js 20+
On first install, Playwright downloads the Chromium headless shell (
postinstallscript)
Related MCP server: Browser Intelligence MCP
Install and run
npx agenteyes-mcp@0.1.0Or from a clone:
git clone https://github.com/tech-lead-bunny/agenteyes-mcp.git
cd agenteyes-mcp
npm install
node index.jsThe process speaks MCP over stdio; connect it from an MCP host (Claude Desktop, Cursor, etc.).
Tools
Tool | Description |
| Open a public |
| Same page context without screenshots (title, a11y, text) |
screenshot_url parameters
url(required) — public http(s) URLfull_page(optional, defaultfalse) — capture full scroll heightsegment_height(optional, default0) — whenfull_pageis true and the page is taller than this value, capture stacked viewport PNGs of this height (top to bottom), then one combined accessibility + text blockwidth/height(optional) — viewport size (defaults 1280×720)
Security (SSRF)
URLs are checked before navigation and again on the final URL after redirects:
Only
http:andhttps:DNS resolution must not point at private/local addresses (localhost, loopback, RFC1918, link-local
169.254.0.0/16,fe80::/10,::1, IPv4-mapped IPv6, etc.)
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"agenteyes": {
"command": "npx",
"args": ["-y", "agenteyes-mcp@0.1.0"]
}
}
}Cursor
In Cursor Settings → MCP, add a stdio server:
{
"mcpServers": {
"agenteyes": {
"command": "npx",
"args": ["-y", "agenteyes-mcp@0.1.0"]
}
}
}Or use a local path after npm install in this repo:
{
"mcpServers": {
"agenteyes": {
"command": "node",
"args": ["/absolute/path/to/agenteyes-mcp/index.js"]
}
}
}Example prompt
Use the
screenshot_urltool onhttps://example.comwithfull_page: true. Summarize the page title and main message from the returned text, and describe what you see in the screenshot.
Limits (v0)
No hosted API — run the MCP server locally (or wherever your host spawns it)
No authentication or rate limiting in the server itself
Public URLs only — private networks and metadata endpoints are blocked
Chromium only — no Firefox/WebKit; no persistent login sessions between calls
One browser process, one page per tool call — pages are always closed after each call
Best-effort rendering — heavy SPAs, infinite scroll, or bot blocking may produce incomplete captures
Segmented full-page capture returns multiple PNGs (not a single stitched image)
MCP registry
mcp.so — primary listing target; submission to the registry is planned once
0.1.0is on npm.awesome-mcp — PR to add
agenteyes-mcpplanned the same week as the npm publish.
License
MIT — see LICENSE.
Available Tools
2 toolsget_page_textA
Open a URL in headless Chromium and return the page title, accessibility snapshot, and visible text (no screenshot).
Inputs: url (required).
screenshot_urlB
Open a URL in headless Chromium and return PNG screenshot(s), an accessibility snapshot, and visible page text.
Inputs: url (required), width, height, full_page, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools are mostly distinct: screenshot_url includes screenshots, while get_page_text does not. However, both return accessibility snapshots and visible text, creating some overlap that could lead to arbitrary selection when only text/snapshot is needed.
Both names use snake_case, but verb patterns are inconsistent: 'screenshot' acts as a verb/noun, while 'get_page_text' uses the verb 'get'. The mix is readable but not a predictable pattern.
Two tools is thin for a web content extraction service. While each tool has a role, the surface feels minimal and could benefit from additional focused tools (e.g., raw HTML, links).
Core capabilities (screenshot and text/snapshot) are covered, but notable gaps exist: no way to retrieve raw HTML, page links, or interact with the page. Agents may hit dead ends for structured data extraction.
Maintenance
Related MCP Connectors
Hosted browser for agents: open pages, search the web, extract data, read PDFs and take screenshots.
A real browser for your agent: screenshots, page checks, Markdown and PDFs.
Give your agent eyes: screenshots of any web page it can see, pages as markdown, and PDFs.
Let your AI agent see any public web page: one screenshot tool, returns the page as an image.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables agents to take screenshots and extract text from web pages using a persistent Chrome browser via CDP, with built-in SSRF protection.MIT
- AlicenseAqualityBmaintenanceEnables AI agents to capture screenshots, scrape structured page content, and run automated visual checks on live websites via a headless Chromium browser.3MIT
- AlicenseAqualityCmaintenanceEnables AI coding agents to open and exercise web applications in an isolated Chromium browser, capture screenshots and runtime/network diagnostics, and run deterministic page checks with linked evidence.121MIT

JsonLink MCP Serverofficial
AlicenseAqualityCmaintenanceEnables AI agents to read any web page as clean Markdown, pull title/description/preview metadata, capture desktop, mobile, or full-page screenshots, and list every link or image on a URL. JavaScript-heavy pages are rendered in a real browser and blocked requests retried through a proxy, so agents can reach content they'd otherwise miss.542 npmMIT