PlayMCP Browser Automation Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| openBrowserC | Launch a new browser instance |
| navigateC | Navigate to a URL |
| typeC | Type text into an element |
| clickD | Click an element |
| moveMouseC | Move mouse to coordinates |
| scrollC | Scroll the page by specified amounts with enhanced feedback |
| screenshotD | Take a screenshot |
| getPageSourceB | Get the HTML source code of the current page |
| getPageTextB | Get the text content of the current page |
| getPageTitleB | Get the title of the current page |
| getPageUrlB | Get the URL of the current page |
| getScriptsB | Get all JavaScript code from the current page |
| getStylesheetsB | Get all CSS stylesheets from the current page |
| getMetaTagsB | Get all meta tags from the current page |
| getLinksB | Get all links from the current page |
| getImagesB | Get all images from the current page |
| getFormsB | Get all forms from the current page |
| getElementContentC | Get the HTML and text content of a specific element |
| getElementHierarchyC | Get the hierarchical structure of page elements with parent-child relationships |
| executeJavaScriptB | Execute arbitrary JavaScript code on the current page and return the result |
| goForwardA | Navigate forward to the next page in history |
| hoverC | Hover over an element on the page |
| dragAndDropD | Drag and drop from one element to another |
| selectOptionC | Select option(s) in a dropdown or select element |
| pressKeyB | Press a key on the keyboard |
| waitForTextC | Wait for specific text to appear on the page |
| waitForSelectorC | Wait for a specific selector to appear on the page |
| resizeC | Resize the browser viewport |
| handleDialogC | Handle browser dialogs (alerts, confirms, prompts) |
| getConsoleMessagesB | Get console messages from the browser |
| getNetworkRequestsB | Get network requests made by the page |
| uploadFilesC | Upload files through a file input element |
| evaluateWithReturnC | Execute JavaScript code and return the result |
| takeScreenshotC | Take a screenshot of the page or specific element |
| mouseMoveC | Move mouse to specific coordinates |
| mouseClickC | Click at specific coordinates |
| mouseDragC | Drag from one coordinate to another |
| closeBrowserB | Close the browser |
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 38 tools
Several tools have overlapping or redundant purposes, causing confusion. For example, 'evaluateWithReturn' and 'executeJavaScript' appear nearly identical, 'mouseClick' and 'click' differ only in input type, and 'moveMouse' and 'mouseMove' are essentially synonyms. This overlap makes it difficult for an agent to reliably choose the correct tool without trial and error.
The naming conventions are mixed, with some tools using verb_noun patterns like 'getPageTitle' and others using simple verbs like 'click' or 'hover'. While most names are readable, the inconsistency in structure (e.g., 'getElementContent' vs. 'takeScreenshot') and occasional redundancy (e.g., 'screenshot' and 'takeScreenshot') detract from predictability, though not to a chaotic level.
With 38 tools, the count is excessive for a browser automation server, leading to bloat and potential confusion. Many tools could be consolidated (e.g., merging mouse-related actions or JavaScript execution tools), and the high number suggests over-specialization rather than a well-scoped set, making it harder for agents to navigate efficiently.
The tool set covers a wide range of browser automation tasks, including navigation, interaction, content extraction, and debugging. However, there are minor gaps, such as missing tools for handling cookies, managing tabs, or simulating more complex user gestures, which agents might need to work around but core workflows are largely supported.