Render MCP Server
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., "@Render MCP Server Open localhost:3000, fill Email with test@example.com, and click Save"
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.
@meiti/render
Render testing built for AI agents, not for people.
Today an agent tests a screen like a person would: take a screenshot, send it to a vision model, guess where to click, take another screenshot. It is slow, expensive and fragile. @meiti/render gives the agent what it actually needs:
A map of the screen instead of a picture. Every element that matters, with its role, name, text, value, state and position, as text. It takes a few milliseconds and any model can read it.
Actions by intent instead of coordinates.
fill "Email" with ...,click "Save". The element is found by its role, label or visible text. If it is not there, the answer says what is.Seeing by comparing maps. Act, scan, compare with the previous map: what appeared, what disappeared, what changed, what moved. "Nothing changed" is information too: a button that does nothing.
What a screenshot never shows. The requests sent to the server and their status, page errors, native dialogs.
Visual issues measured exactly, no vision model needed. Horizontal overflow, cut text, covered or off-screen elements, small touch targets, low contrast, broken images, buttons without a name.
Before and after. Compare two versions of an app (home page plus up to 3 linked pages, phone and desktop): worse, better or the same.
It works with apps that render inside same-origin iframes and waits until the screen is stable (two identical maps in a row and nothing loading) before reading it.
Use it from an agent (MCP)
npx -y @meiti/renderAdd it to any MCP client as a stdio server with the command npx -y @meiti/render. It needs Node 18 or newer and a Chrome: the one puppeteer downloads, otherwise the Chrome installed on the machine, or the executable you set in MEITI_RENDER_CHROME.
Tools:
Tool | What it does |
| Opens a URL (any size: 375 for a phone) and returns the map and its visual issues. |
| One action by intent ( |
| Checks what you expect: yes or no, with the exact proof. |
| Scans the current screen again. |
| Compares two versions of the same app. |
| Closes a session. |
Example of what the agent reads after render_act {"type": "click", "target": "Add"}:
Acted on button:Add in 858 ms.
What changed: appeared 1: listitem:Milk; moved 4
Requests:
- POST http://localhost:3000/api/items → 201
Page errors: noneRelated MCP server: kogiQA MCP Web Browser
Use it from code
import puppeteer from 'puppeteer';
import { SesionRender } from '@meiti/render';
const browser = await puppeteer.launch();
const session = await SesionRender.abrir(browser, 'http://localhost:3000', { ancho: 375, alto: 812 });
await session.hacer({ tipo: 'llenar', objetivo: 'Email', valor: 'ana@example.com' });
const result = await session.hacer({ tipo: 'clic', objetivo: 'Save' });
console.log(result.cambio.resumen);
console.log(session.verificar([{ pedido: { metodo: 'POST', url_contiene: '/api/users', status: 201 } }]));Verified by Healer
@meiti/render is a MEITI tool, verified by Healer with exams that have known answers, run on every version:
Exam | Result |
Visual issues (one planted issue per page, plus clean pages) | 11 of 11, 0 false alarms, ~4 ms per scan |
Actions and expectations (JavaScript error, silent 500, missing button) | 10 of 10 |
Apps rendered in iframes, loading states, native dialogs | 7 of 7 |
Before and after (worse, better, same) | 3 of 3 |
License
MIT
Available Tools
6 toolsrender_actA
Do one action by INTENT (no coordinates) and return what changed on the screen: elements that appeared, disappeared, changed or moved (or "nothing changed": a control that does nothing), requests to the server with their status, page errors and native dialogs (accepted automatically). target is an id from the map (like "button:Save"), a label or a visible text; if it is not on the screen, the answer lists what is there.
Inputs: action (required), session (required), include_map.
render_closeC
Close a session.
Inputs: session (required).
render_compareA
Compare two versions of the same app (for example before and after a change): the home page and up to 3 pages it links to, on a phone and a desktop. Says WORSE if a visual issue appears, an interactive element disappears or a page stops opening; BETTER if issues were fixed; SAME otherwise.
Inputs: url_after (required), url_before (required).
render_expectA
Check what you expect against the current screen and the last action; each answer is yes or no with its proof (the exact element or request). Expectations: {"exists": "..."}, {"not_exists": "..."}, {"text": "...", "contains": "..."}, {"appeared": "..."}, {"disappeared": "..."}, {"no_changes": true}, {"no_issues": true | ["contraste", ...]}, {"no_errors": true}, {"request": {"method": "POST", "url_contains": "/api/x", "status": 201}}.
Inputs: session (required), expectations (required).
render_openA
Open a page in a real browser and return its MAP: every element that matters (role, name, text, value, state, position) plus visual issues measured exactly (horizontal overflow, cut text, covered or off-screen elements, small touch targets, low contrast, broken images, unnamed buttons). Works inside same-origin iframes. Returns a session id for render_act, render_expect and render_scan.
Inputs: url (required), width, height.
render_scanB
Scan the current screen again (waits until it is stable) and return the full map with its visual issues.
Inputs: session (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a mostly distinct role: open, act, expect, scan, compare, close. There is some conceptual overlap between render_open and render_scan (both return a map) and between render_act and render_expect (both report changes/no-changes), but the descriptions make the intended usage clear enough to avoid most misselection.
All six tools follow the same predictable render_verb pattern in snake_case: render_open, render_act, render_expect, render_scan, render_compare, render_close. No naming inconsistencies or mixed conventions are present.
Six tools is well-scoped for a browser automation and visual verification server. Each tool covers a distinct phase of the workflow, and no tool feels redundant or missing at the count level.
The surface covers the core lifecycle: open a page, act, check expectations, rescan, compare versions, and close the session. Minor gaps exist around explicit navigation/reload or session listing, but agents can work around those using render_open and render_act.
Maintenance
Related MCP Connectors
Browser-based QA for AI-built software. Test pages with real browsers via agents.
Hosted browser for AI agents: screenshots, post-JS DOM, console, WCAG. No install, no API key.
Website checker for AI coding agents. Measures your site in a real browser, with evidence.
Write, run and check natural-language browser tests of your web app from your AI assistant.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to autonomously interact with and test web applications in a real browser, providing DOM/Accessibility tree extraction, runtime telemetry, screenshot capture, and Markdown test reports.9 npm1MIT
- AlicenseNot gradedqualityBmaintenanceEnables LLM agents to drive a selector-free browser through natural language, so they can debug styling and console errors, map and document web apps, and generate or run end-to-end and exploratory tests without screenshots.908 npm88MIT
- AlicenseNot gradedqualityAmaintenanceEnables an AI agent to measure live web and responsive UIs across mobile and desktop sessions, returning contrast ratios, touch-target sizes, overflow, clipping, and theme-drift problems as precise text findings tied to selectors instead of screenshots to guess from. Agents can also navigate, tap, type, scroll, switch device profiles and themes, and read the notes a human pins in the shared panel alongside the exact frame being viewed.95 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to inspect live web and responsive UIs across mobile and desktop sessions, returning measured text findings on contrast ratios, touch-target sizes, overflow, and theme drift instead of screenshot guesses. It also lets a human and the agent share one live panel, so the agent can navigate, tap, and type while reading the user's pinned notes and frames.95 npmMIT