Configurable Puppeteer 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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| puppeteer_navigateB | Navigate to a URL |
| puppeteer_screenshotB | Take a screenshot of the current page or a specific element |
| puppeteer_clickC | Click an element on the page |
| puppeteer_fillC | Fill out an input field |
| puppeteer_selectC | Select an element on the page with Select tag |
| puppeteer_hoverC | Hover an element on the page |
| puppeteer_evaluateB | Execute JavaScript in the browser console |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Browser console logs |
TDQS
Scored across 7 tools
Every tool has a clearly distinct purpose with no ambiguity. Clicking, evaluating JavaScript, filling inputs, hovering, navigating, taking screenshots, and selecting dropdown elements are all separate browser automation operations that an agent can easily distinguish. The descriptions clearly differentiate each action.
All tools follow a perfect verb_noun pattern with consistent snake_case naming (puppeteer_click, puppeteer_evaluate, etc.). The 'puppeteer_' prefix creates a clear namespace, and the action verbs (click, evaluate, fill, hover, navigate, screenshot, select) are consistently descriptive and parallel in structure.
Seven tools is well-scoped for a Puppeteer automation server. This provides core browser interaction capabilities without being overwhelming. Each tool earns its place by covering essential operations like navigation, interaction, evaluation, and capture that form a complete automation workflow.
The toolset covers most essential Puppeteer operations well, including navigation, interaction, evaluation, and screenshots. Minor gaps exist - there's no explicit tool for waiting/loading states, keyboard input, or cookie/session management - but agents can work around these using evaluate or other tools. Core browser automation workflows are well-supported.