Skip to main content
Glama
Render MCP Server

Render MCP Server

by meiti-dev

render_act

Run browser UI actions by intent without coordinates and return on-screen changes, network requests, page errors, and dialogs so agents can verify test steps.

Instructions

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.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "session": "<session>",
      "action": "<action>"
    },
    "name": "render_act"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes{ "type": "click" | "fill" | "select" | "check" | "key" | "goto", "target": "...", "value": "...", "key": "Enter", "url": "..." }
sessionYes
include_mapNoAlso return the full new map. Default false (the change is usually enough).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the load and does it well: it discloses that native dialogs are accepted automatically (a real side effect), that server requests and page errors are surfaced, and that 'nothing changed' is a legitimate outcome. It stops short of stating session lifecycle or whether a failed target lookup consumes the action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action, then the return contract, then target resolution rules — a sensible order. The middle enumeration of return categories is dense but each item is informative; only slight tightening would help.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must explain returns — and it does, covering diffs, network status, errors, and dialogs. For a 3-parameter nested-action tool that is nearly enough; the unexplained session parameter is the one loose end.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers 67% of parameters, and the description adds genuine meaning the schema does not: target accepts a map id like "button:Save", a label, or visible text, and on a miss the response enumerates what is on screen. That fallback contract is the most valuable part of the definition. session and include_map are left to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and unit of work ("Do one action by INTENT (no coordinates)") plus the return payload, which is far more precise than a bare name. It implicitly separates itself from render_compare/render_scan by being single-action and diff-returning, but it never names a sibling to make that contrast explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: one action per call, intent-based rather than coordinate-based. There is no statement of when to prefer this over render_compare, render_expect, or render_scan, and no prerequisites such as needing an open session from render_open.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.