PuppeteerMCP 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 |
|---|---|
| screenshotB | Capture screenshots of web pages at multiple viewport breakpoints using Puppeteer |
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 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear, distinct purpose focused on capturing screenshots at multiple viewport breakpoints.
The tool name 'screenshot' follows a simple, descriptive noun-based pattern. Since there is only one tool, consistency is inherently perfect with no deviations or mixed conventions to evaluate.
A single tool is too few for a server named 'PuppeteerMCP Server', which suggests broader web automation capabilities beyond just screenshots. This feels thin and under-scoped for the apparent domain of Puppeteer-based web interactions.
The tool surface is severely incomplete for a Puppeteer server, covering only screenshot functionality. Obvious gaps include navigation, form interaction, content extraction, and other core web automation tasks, which will likely cause agent failures in broader workflows.