Skip to main content
Glama

Run browser check

browser_run

Run a Playwright script against the preview in the sandbox browser. Bindings: page, context, request, expect, baseUrl, snapshot(), screenshot('label'). Navigate with page.goto(baseUrl) or page.goto('/path'); omit base_url. At most 3 screenshots per call are returned: scroll the target into view and let it settle before each. Prefer expect() for checks. timeout_ms stops the script after that many milliseconds.

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": {
      "title": "<title>",
      "code": "<code>"
    },
    "name": "browser_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeYesAsync Playwright JS body; screenshot('label') captures stills (max 3 returned). Use baseUrl or relative paths; *.mythex.ai URLs are not reachable from the sandbox.
titleYes
base_urlNo
project_idNoProject id (or use session from use_project)
timeout_msNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / properties / timeout_ms / maximum
      Removed value: -180000
    • removedInput schema / properties / timeout_ms / minimum
      Removed value: -10000
    • changedInput schema / properties / timeout_ms / type
      Previous value: -"integer"New value: +"number"
  2. Changed4 schema fields changed
    • changedInput schema / properties / code / description
      Previous value: -"Async Playwright JS body; screenshot('label') captures stills. base_url defaults to the local preview; *.mythex.ai URLs are not reachable from the sandbox."New value: +"Async Playwright JS body; screenshot('label') captures stills (max 3 returned). Use baseUrl or relative paths; *.mythex.ai URLs are not reachable from the sandbox."
    • addedInput schema / properties / timeout_ms / maximum
      Added value: +180000
    • addedInput schema / properties / timeout_ms / minimum
      Added value: +10000
    • changedInput schema / properties / timeout_ms / type
      Previous value: -"number"New value: +"integer"
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare the safety profile (not read-only, open-world, not idempotent, non-destructive) and say nothing about execution semantics. The description adds real context beyond them: the available bindings, the hard cap of three screenshots returned per call, the need to scroll and settle before capturing, and that timeout_ms aborts the script. It still omits what happens on script error or what the call returns.

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 and then the bindings, and every clause carries information about calling the tool. The telegraphic, semicolon-heavy style is dense but occasionally reads as a list of fragments rather than a coherent instruction set.

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?

For an open-world execution tool with no output schema and only 40% parameter documentation, the description covers the scripting model, the screenshot limit, and timeout behavior. Gaps remain around the return value (what a successful run yields besides screenshots), the role of title, and how failures surface.

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?

With schema coverage at 40%, the description compensates well for the three most important parameters: code (async body, screenshot('label'), baseUrl or relative paths), base_url (omit it when using baseUrl), and timeout_ms (stops the script). It says nothing about title or project_id, leaving two parameters undocumented in both places.

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?

"Run a Playwright script against the preview in the sandbox browser" is a specific verb plus resource and makes clear this is browser automation, not shell execution. It never names a sibling such as bash, so an agent must infer the boundary itself, which keeps it just short of a 5.

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?

Guidance is present but is about how to write the script (page.goto with baseUrl or a relative path, omit base_url, prefer expect() for checks) rather than when to pick this tool over bash or get_preview. Usage context is implied by "preview in the sandbox browser" with no exclusions or prerequisites stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources