Scrapybara MCP
by Scrapybara
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ACT_MODEL | Yes | The model to use for the 'act' tool ('anthropic' or 'openai') | |
| AUTH_STATE_ID | No | Optional ID for authenticating the browser | |
| SCRAPYBARA_API_KEY | Yes | Your Scrapybara API key from scrapybara.com |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_instance | Start a Scrapybara Ubuntu instance. Use it as a desktop sandbox to access the web or run code. Always present the stream URL to the user afterwards so they can watch the instance in real time. |
| get_instances | Get all running Scrapybara instances. |
| stop_instance | Stop a running Scrapybara instance. |
| bash | Run a bash command in a Scrapybara instance. |
| act | Take action on a Scrapybara instance through an agent. The agent can control the instance with mouse/keyboard and bash commands. |