Puppeteer Real Browser MCP 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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_initB | Initialize a new browser instance with anti-detection features and automatic Chrome path detection |
| navigateC | Navigate to a URL |
| get_contentA | Recommended method to get page content (HTML or text) - More reliable than screenshots for content analysis and navigation tasks |
| clickC | Click on an element |
| typeB | Type text into an input field |
| waitC | Wait for various conditions |
| browser_closeA | Close the browser instance |
| solve_captchaC | Attempt to solve CAPTCHAs (if supported) |
| random_scrollA | Perform random scrolling with natural timing |
| find_selectorB | Find CSS selector for element containing specific text |
| save_content_as_markdownB | Extract page content and save it as a formatted markdown file |
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 11 tools
Each tool has a clearly distinct purpose: navigation, interaction, content retrieval, and browser lifecycle. Even get_content and save_content_as_markdown are differentiated by returning versus saving content. No two tools overlap in function.
Tool names mix bare verbs (click, type, wait), verb_noun pairs (get_content, find_selector), and a prefixed pair (browser_init, browser_close). While readable, the inconsistency in naming style is noticeable and lacks a single predictable pattern.
With 11 tools, the count is well within the ideal range for a browser automation server. Each tool covers a core aspect of browsing without redundancy or bloat.
The tool set covers basic navigation, interaction, waiting, content extraction, and even captcha solving. However, common browser automation features like taking screenshots, executing JavaScript, getting the current URL/title, or handling browser history are missing, leaving some gaps for general browser use.