Skip to main content
Glama
frsorrentino

Chrome Bridge

by frsorrentino
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

handoff

Idempotent

Hands the browser to a user for tasks only a person can do, like 2FA, CAPTCHA, login, or choices, showing a page banner and waiting to resume when done.

Instructions

Hand the browser to the user for what only a person can do — 2FA, CAPTCHA, login, a choice — and wait: a banner in the page shows your message with Done/Cancel, the call returns on click or timeout, redirects included. pick_element: the user clicks an element and you get its selector. Never type credentials yourself. ask: the user types a reply in the banner ("which of the three?") and you get it as answer. pick_max: with pick_element, up to N elements; the user presses Done when finished.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
askNoShow a text box in the banner; the reply comes back as answer
tab_idNoTarget tab; omitted = last tab navigated in this session, else the active one
messageYesWhat the user should do, one line
timeoutNoms to wait for the click, default 5 min
pick_maxNoWith pick_element: up to N elements, the user presses Done when finished
in_terminalNoAlso ask in the Claude Code terminal (MCP elicitation) when the client supports it; the first answer wins. Not for pick_element
pick_elementNoAsk the user to click an element; returns its selector, text and box

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.28.0
    • addedInput schema / properties / ask
      Added value: +{
+  "default": false,
+  "description": "Show a text box in the banner; the reply comes back as answer",
+  "type": "boolean"
+}
    • addedInput schema / properties / in_terminal
      Added value: +{
+  "default": true,
+  "description": "Also ask in the Claude Code terminal (MCP elicitation) when the client supports it; the first answer wins. Not for pick_element",
+  "type": "boolean"
+}
    • addedInput schema / properties / pick_max
      Added value: +{
+  "default": 1,
+  "description": "With pick_element: up to N elements, the user presses Done when finished",
+  "type": "number"
+}
  2. Addedv1.16.1

TDQS

A4.7/5.0
Behavior5/5

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

Goes well past the annotations by describing the interaction contract: a banner with the message and Done/Cancel, return triggered by click or timeout, redirects included, default 5-minute wait. It also discloses the answer-passing behavior of ask and the selector/text/box return of pick_element, which the annotations do not cover.

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?

Front-loaded with the core purpose and the safety rule before the mode details, and every clause carries information. Slightly dense/long as a single run-on paragraph listing four modes, which costs a point versus a crisply structured alternative.

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

Completeness4/5

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

For a 7-param, no-output-schema tool, the description supplies the missing return semantics (selector, answer, Done signal) and the safety constraint. It could say more about what happens on timeout expiry or Cancel, but nothing essential for correct invocation is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds genuine semantic context beyond the schema — it explains what the mode flags actually produce ('you get its selector', 'the reply comes back as answer', 'user presses Done when finished') and clarifies tab_id fallback and timeout behavior.

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

Purpose5/5

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

States a precise verb+resource+scope: handing the browser over to the human for actions only a person can perform, with named conditions (2FA, CAPTCHA, login, a choice). An agent can immediately separate this from automated siblings like click, type_text, and fill_form.

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

Usage Guidelines5/5

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

Explicitly enumerates when to use it (2FA, CAPTCHA, login, a choice) and adds a clear negative rule: 'Never type credentials yourself,' which routes the agent away from type_text/fill_form. The three mode flags (pick_element, ask, pick_max) are each paired with the situation that selects them.

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

Deploy Server

Other Tools