agent-browser
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Server port | 5888 |
| BASE_URL | No | Public URL path for screenshots | /screenshots |
| CERT_PATH | No | SSL certificate path | /etc/letsencrypt/live/test2.infinitrocyber.com |
| ENABLE_HTTPS | No | Enable HTTPS with Let's Encrypt certs | false |
| MCP_SCRIPT_PATH | No | Path to compiled MCP server | ./dist/index.js |
| AGENT_BROWSER_SCREENSHOT_DIR | No | Directory for saved screenshots | ./screenshots |
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 |
|---|---|
| browser_openC | Open URL in browser |
| browser_clickC | Click element by selector or @ref |
| browser_fillC | Clear and fill input |
| browser_typeC | Type text into input |
| browser_pressC | Press key (Enter, Tab, etc) |
| browser_snapshotC | Get accessibility tree with refs |
| browser_screenshotD | Take screenshot |
| browser_readC | Read page content or fetch URL |
| browser_evalD | Execute JavaScript |
| browser_waitC | Wait for element/text/URL |
| browser_closeC | Close browser |
| browser_navigateC | Back/forward/reload |
| browser_getC | Get text/html/value/url/title |
| browser_tabD | Manage tabs |
| browser_networkD | Network requests/routes |
| browser_cookieD | Manage cookies |
| browser_storageC | Manage localStorage/sessionStorage |
| browser_dialogD | Handle dialogs |
| browser_scrollC | Scroll page |
| browser_hoverD | Hover element |
| browser_selectC | Select dropdown option |
| browser_findC | Find elements semantically |
| browser_setC | Set viewport/device/geo/media |
| browser_stateC | Save/load auth state |
| browser_streamD | WebSocket streaming |
| browser_consoleC | View/clear console logs and errors |
| browser_traceC | Record trace |
| browser_frameD | Switch frame |
| browser_batchC | Execute multiple commands |
| browser_reactD | React devtools |
| browser_vitalsD | Web Vitals metrics |
| browser_a11yD | Accessibility audit |
| browser_profileD | Chrome profiles |
| browser_sessionD | Session management |
| browser_skillsD | List/get skills |
| browser_installC | Install Chrome |
| browser_doctorD | Diagnose install |
| browser_diffC | Diff snapshots/screenshots |
| browser_chatD | Natural language browser control |
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 39 tools
Each tool targets a distinct browser operation (e.g., click, fill, hover, scroll) with no overlapping responsibilities. Even similar tools like get and read are differentiated by specific data returning or page fetching, and snapshot is distinct from screenshot.
All tools follow a consistent 'browser_<verb>' pattern (e.g., open, click, fill, type, press), with no mixed conventions or vague names. The naming is predictable and clearly conveys each tool's action.
With 39 tools, the count exceeds the typical range and feels heavy for most workflows. While the browser automation domain is broad, many tools are granular (e.g., browser_console, browser_trace), leading to potential selection overhead.
The tool set covers a comprehensive range of browser interactions: navigation, element actions, state management, debugging, performance monitoring, and network control. Minor gaps exist (e.g., file upload, form submission explicit handling), but most core workflows are well-supported.