Skip to main content
Glama
djannot

Puppeteer Vision MCP Server

by djannot

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoThe port for the HTTP server in SSE or HTTP mode3001
USE_SSENoDeprecated: Set to true to enable SSE mode over HTTP. Use TRANSPORT_TYPE=sse instead.
API_BASE_URLNoCustom API endpoint URL. Use this to connect to alternative OpenAI-compatible providers (e.g., Together.ai, Groq, Anthropic, local deployments).https://api.openai.com/v1
VISION_MODELNoThe model to use for vision analysis. Can be any model with vision capabilities.gpt-4.1
OPENAI_API_KEYYesYour API key for accessing the vision model
TRANSPORT_TYPENoThe transport protocol to use. Options: stdio (default), sse, httpstdio
DISABLE_HEADLESSNoSet to true to run the browser in visible modefalse

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/djannot/puppeteer-vision-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server