local-browser-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HEADLESS | No | Set to 'true' to run browser in headless mode (background). Default is false. | false |
| GOOGLE_AI_KEY | No | API key for Google Gemini AI image generation. Required to use the generate_image tool. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| navigate_to_urlB | Navigate the browser to a specific URL |
| take_screenshotB | Take a screenshot of the current page |
| click_elementC | Click on an element specified by CSS selector |
| type_textA | Type text into an input field specified by CSS selector |
| wait_for_elementB | Wait for an element to appear on the page |
| get_page_infoA | Get information about the current page (title, URL, etc.) |
| scroll_pageC | Scroll the page up or down |
| refresh_pageA | Refresh the current page |
| go_backA | Navigate back in browser history |
| go_forwardA | Navigate forward in browser history |
| generate_imageA | Generate images using Google Gemini 2.0 Flash Preview Image Generation (requires GOOGLE_AI_KEY environment variable) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Each tool has a distinct purpose: clicking, navigating, scrolling, typing, waiting, etc. No two tools overlap in functionality, even the optional image generation is separate. Agents can easily distinguish them.
All tools use snake_case with a consistent verb_noun pattern (e.g., click_element, navigate_to_url, take_screenshot). The naming is uniform and predictable, making it easy for agents to infer functionality.
11 tools is well-scoped for a browser automation server, covering essential actions without being excessive. Each tool serves a clear role in the workflow.
The tool set covers core browser automation tasks (navigation, clicking, typing, scrolling, screenshots, page info, waiting). Minor gaps include lack of text extraction from elements or page source retrieval, but these are not critical for common workflows.