playwright-browser-evaluate
To run JavaScript in the page context, evaluate an expression on the page or a specific element for inspection or manipulation.
When & Why to Use This Skill
The playwright-browser-evaluate skill enables the execution of custom JavaScript expressions directly within a browser's page context. It is a powerful tool for advanced web automation, allowing users to perform deep DOM manipulation, inspect runtime variables, and interact with complex web elements that are otherwise inaccessible through standard automation commands.
Use Cases
- Dynamic Data Extraction: Scraping content from Single Page Applications (SPAs) or websites where data is rendered dynamically via JavaScript.
- Automated UI Testing: Verifying the internal state of web components or triggering specific client-side events to ensure interface reliability and performance.
- Web Interaction & Manipulation: Programmatically handling complex user flows such as infinite scrolling, custom form submissions, or real-time CSS modifications.
- Advanced Page Inspection: Accessing global JavaScript objects or hidden element properties to troubleshoot and debug web-based agent workflows.
| name | playwright-browser-evaluate |
|---|---|
| description | "To run JavaScript in the page context, evaluate an expression on the page or a specific element for inspection or manipulation." |
Usage
Use the MCP tool dev-swarm.request to send the payload as a JSON string:
{"server_id":"playwright","tool_name":"browser_evaluate","arguments":{}}
Tool Description
Evaluate JavaScript expression on page or element
Arguments Schema
The schema below describes the arguments object in the request payload.
{
"type": "object",
"properties": {
"function": {
"type": "string",
"description": "() => { /* code */ } or (element) => { /* code */ } when element is provided"
},
"element": {
"type": "string",
"description": "Human-readable element description used to obtain permission to interact with the element"
},
"ref": {
"type": "string",
"description": "Exact target element reference from the page snapshot"
}
},
"required": [
"function"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
Background Tasks
If the tool returns a task id, poll the task status via the MCP request tool:
{"server_id":"playwright","method":"tasks/status","params":{"task_id":"<task_id>"}}