Browser Agent MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_BROWSER_TYPE | No | The browser type to use. Supported values: chrome (default), firefox, webkit, edge | chrome |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_set_viewportC | Change the browser's viewport size and scale factor |
| browser_navigateC | Navigate to a specific URL |
| browser_screenshotC | Capture a screenshot of the current page or a specific element |
| browser_clickC | Click an element on the page |
| browser_fillC | Fill a form input with text |
| browser_selectC | Select an option from a dropdown menu |
| browser_hoverC | Hover over an element on the page |
| browser_evaluateC | Execute JavaScript in the browser context |
| api_getC | Perform a GET request to an API endpoint |
| api_postC | Perform a POST request to an API endpoint |
| api_putC | Perform a PUT request to an API endpoint |
| api_patchC | Perform a PATCH request to an API endpoint |
| api_deleteC | Perform a DELETE request to an API endpoint |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Browser console logs |
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/imprvhub/mcp-browser-agent'
If you have feedback or need assistance with the MCP directory API, please join our Discord server