Skip to main content
Glama

browser_bridge

Connect to a user-approved browser tab through their extension to navigate, read, screenshot, and manage only that tab; no access occurs before the user grants it.

Instructions

Drive the browser the USER has open, through their extension.

action: status | connect | tabs | navigate | read | screenshot | disconnect. The user connects a tab in the extension (one click, with Chromium's own "debugging this browser" bar); Body-MCP then acts only on that tab. Nothing is read or navigated before the user connects it.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "browser_bridge"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNo
actionNostatus

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

B3.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden; it does disclose the key behavioral trait that Body-MCP acts only on the user-connected tab and reads/navigates nothing before connection. It omits what navigate does to the user's live tab (a disruptive mutation), error behavior, and what each action returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core capability is front-loaded in the first sentence, followed by the action vocabulary and the connection constraint. The parenthetical about Chromium's 'debugging this browser' bar is slightly verbose but justifies itself by explaining the one-click setup.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with no annotations and no output schema, the description covers the permission model and action set adequately. It leaves gaps around which parameters apply to which actions and what the read/tabs/screenshot actions yield.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it does partially by enumerating the valid action values that the schema exposes only as a free-form string with default 'status'. The 'url' parameter is never mentioned, leaving its binding to the navigate action undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: driving the browser the user already has open, via their extension. It is clearly distinct from read-only introspection siblings, though it does not explicitly differentiate itself from attach_browser/detach_browser.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The action list (status | connect | tabs | navigate | read | screenshot | disconnect) implies the modes of use, and the description states the prerequisite that the user must connect a tab first. However, it gives no explicit when-to-use/when-not guidance relative to sibling tools such as attach_browser or eyes_see_browser.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.