Puppeteer Vision MCP Server
by djannot
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | The port for the HTTP server in SSE or HTTP mode | 3001 |
| USE_SSE | No | Deprecated: Set to true to enable SSE mode over HTTP. Use TRANSPORT_TYPE=sse instead. | |
| API_BASE_URL | No | Custom 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_MODEL | No | The model to use for vision analysis. Can be any model with vision capabilities. | gpt-4.1 |
| OPENAI_API_KEY | Yes | Your API key for accessing the vision model | |
| TRANSPORT_TYPE | No | The transport protocol to use. Options: stdio (default), sse, http | stdio |
| DISABLE_HEADLESS | No | Set to true to run the browser in visible mode | false |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
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