Agenteyes MCP
Give coding agents real eyes: one tool call returns a screenshot PNG plus the accessibility tree and page text; segmentheight paginates long pages into readable tiles.
التثبيت
خطوات التثبيت موجودة في التوثيق أدناه. التوثيق
التوثيق
مأخوذ من ملف README للمشروع على GitHub ويُحدَّث أسبوعيًا. تفتح الروابط على GitHub.
المحتويات
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)
Install and run
npx agenteyes-mcp@0.1.0
Or from a clone:
git clone https://github.com/tech-lead-bunny/agenteyes-mcp.git
cd agenteyes-mcp
npm install
node index.js
The process speaks MCP over stdio; connect it from an MCP host (Claude Desktop, Cursor, etc.).
Tools
| Tool | Description |
|---|---|
screenshot_url | Open a public http/https URL; return PNG screenshot(s), accessibility tree, and visible text |
get_page_text | 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.
الأسئلة الشائعة
ما هو Agenteyes MCP؟
Give coding agents real eyes: one tool call returns a screenshot PNG plus the accessibility tree and page text; segmentheight paginates long pages into readable tiles.
كيف أثبّت Agenteyes MCP؟
اتبع خطوات التثبيت في توثيقه المعروض في هذه الصفحة وفي مستودعه.
هل Agenteyes MCP مفتوح المصدر؟
نعم. شيفرته متاحة على GitHub بترخيص MIT.
من يصون Agenteyes MCP؟
ينشره tech-lead-bunny. يدرجه AI.tn لكنه لا يصونه ولا يوصي به.
من القوائم المجتمعية awesome-mcp-servers ومستودع المشروع على GitHub. الإدراج ليس توصية: راجع شيفرة الخادم وصلاحياته قبل منحه الوصول إلى بياناتك.