Render MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEITI_RENDER_CHROME | No | Path to the Chrome executable to use. If not set, the Chrome downloaded by puppeteer is used, otherwise the Chrome installed on the machine. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Test screens like an agent, not like a person: render_open returns a map of the screen; render_act does one action by intent and tells you what changed; render_expect checks what you expect. Compare maps instead of looking at screenshots.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| 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. |
| render_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. |
| 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}}. |
| render_scanB | Scan the current screen again (waits until it is stable) and return the full map with its visual issues. |
| 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. |
| render_closeC | Close a session. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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.