ecobrowser MCP server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AI_BROWSER_LIVE | No | Enable the live-view server. Set to '0' to disable. | 1 |
| AI_BROWSER_HEADED | No | Show the native browser window (default: headless). Set to '1' to show. | 0 |
| AI_BROWSER_LIVE_PORT | No | Preferred live-view port (default 7333). Steps to next free port if busy. | 7333 |
| AI_BROWSER_ALLOW_LOCAL | No | Allow file:// or privileged-scheme navigation (blocked by default). Set to '1' to allow. | 0 |
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_navigateA | Open a URL and return a structured snapshot of the page's interactive elements. |
| browser_snapshotA | Get a structured snapshot of the current page — each interactive element has a stable id you can act on. Cached until the page changes. |
| browser_changesA | Return ONLY what changed since your last snapshot (added/removed/changed elements). Cheaper than a full snapshot — prefer this after an action. |
| browser_findA | Find interactive elements matching a description (e.g. 'search box', 'Sign in button') and get just the matches with their ids — far cheaper than reading a full snapshot when you know what you want. |
| browser_read_textA | Return the visible text content of the current page (truncated). |
| browser_backA | Go back in the browser history. |
| browser_clickA | Click an element by its snapshot id. Returns a fresh snapshot after the action. |
| browser_typeA | Type text into a field by its snapshot id (clears the field first). |
| browser_consoleA | Return console logs and page errors captured on the current page. |
| browser_networkA | Return the network responses (status, method, url) captured on the current page. |
| browser_evaluateA | Run a JavaScript EXPRESSION in the page and return its JSON-serialized result (e.g. |
| browser_extract_linksA | Extract all links on the page as name/href pairs. |
| browser_resetA | Close and discard the current browser session; the next action starts a fresh one. Use to recover from a wedged or crashed page. |
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 13 tools
Each tool has a clearly distinct purpose: navigation, clicking, typing, snapshotting, finding elements, evaluating JavaScript, checking console/network, resetting, etc. Overlap is minimal (e.g., snapshot vs. changes are complementary, not ambiguous).
All tools follow the 'browser_' prefix with snake_case verb_noun pattern (e.g., browser_navigate, browser_click, browser_snapshot). The naming is uniform and predictable.
13 tools cover the core browser automation actions without being too many or too few. The count is well-scoped for the domain, providing necessary functionality without bloat.
The set covers essential browser interactions: navigation, clicking, typing, state inspection, JS evaluation, console/network monitoring, and session reset. Minor gaps exist (e.g., no explicit scrolling or screenshot), but these can be worked around via JS evaluation.