Browser Automation MCP
by PopoverAI
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MODEL_API_KEY | No | API key for the configured model provider (works with any provider) | |
| GEMINI_API_KEY | No | Alternative to MODEL_API_KEY for Gemini (the default model) | |
| OPENAI_API_KEY | No | Only needed for stagehand_demo_video (TTS via gpt-4o-mini-tts) | |
| NGROK_AUTHTOKEN | No | Only needed for cloud: true with localhost URLs | |
| BROWSERBASE_API_KEY | No | Only needed for cloud: true | |
| STAGEHAND_VARIABLES | No | Optional JSON map of variables auto-injected into stagehand_act, stagehand_agent, and stagehand_scenario | |
| BROWSERBASE_PROJECT_ID | No | Only needed for cloud: true | |
| VERCEL_AUTOMATION_BYPASS_SECRET | No | Optional, for Vercel preview deployments |
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/PopoverAI/browser-automation'
If you have feedback or need assistance with the MCP directory API, please join our Discord server