jevbridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JEVBRIDGE_PORT | No | Port for the JevBridge MCP server. Must match the port set in the extension options. Defaults to 10577. | 10577 |
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_statusA | Report bridge + extension connection state and the currently targeted tab. Call this first if anything behaves unexpectedly: it distinguishes "no extension connected" from "no tab attached". |
| browser_tabsA | List open tabs in the real browser (id, title, url, active). Use a tab id with the other tools to target a specific tab; omit to use the active tab. |
| browser_navigateA | Navigate the target tab to a URL and return the element table once loaded. |
| browser_observeA | Read the target tab as an element table: one numbered, actionable control per line (e12 btn "Sign in"). Refs (e12) stay stable across observations of the same page. Read this, then act on the refs. |
| browser_actA | Run a list of operations on the target tab in order, then return the fresh element table. ops: [{op:"click",ref:"e12"} | {op:"type",ref:"e7",text:"..."} | {op:"select",ref:"e8",value:"..."} | {op:"key",key:"Enter"} | {op:"scroll",dy:600} | {op:"wait",ms:500}]. |
| browser_assertA | Prove an outcome instead of inferring it. Provide one of: contains (page text includes string), url_includes (current url contains string), ref_visible (a ref is present and visible). Returns pass/fail. |
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 6 tools
Each tool targets a distinct concern: listing tabs, checking connection/target state, navigating, reading the page, acting on the page, and asserting outcomes. The descriptions clearly separate browser_status from browser_tabs by emphasizing connection state versus the full tab list.
All tools share a consistent browser_ prefix and lowercase style, which makes the set predictable. However, the second part mixes nouns (tabs, status) with verbs (navigate, observe, act, assert), so the pattern is not perfectly uniform.
Six tools is a well-scoped size for browser automation. Each tool covers a necessary phase of the workflow without redundancy or bloat.
The core browser automation lifecycle is covered: list tabs, target, navigate, observe, act, and assert. Minor gaps exist around tab lifecycle operations like creating or closing tabs, but these don't prevent typical automation workflows.