Skip to main content
Glama
Sign In
pironjulien

nexus-browser

by pironjulien
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

browser_check_handoff

Read-onlyIdempotent

Detects 2FA prompts, CAPTCHAs, and Cloudflare Turnstile screens so agents can pause and hand off control to the user for manual completion.

Instructions

Proactively detects a 2FA screen (SMS, Google Authenticator), a CAPTCHA or Cloudflare Turnstile.

Input Schema

NameRequiredDescriptionDefault
tab_idYesYour tab's id (from browser_new_tab, or a tab adopted with browser_adopt_tab).

Output Schema

NameRequiredDescriptionDefault
dataYes
statusYes
warningNoEmergency stop hotkey not held, or similar notice
untrusted_noteNoPage text that looks like instructions aimed at an AI

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv2.31.6
    • addedOutput schema / $defs
      Added value: +{
+  "Handoff": {
+    "additionalProperties": true,
+    "description": "handoffRequired: a 2FA screen, a CAPTCHA or Cloudflare (type) needs the user.",
+    "properties": {
+      "dialog": {
+        "$ref": "#/$defs/PageDialog"
+      },
+      "dialogOpened": {
+        "type": "boolean"
+      },
+      "handoffRequired": {
+        "type": "boolean"
+      },
+      "message": {
+        "type": "string"
+      },
+      "pendingDialogs": {
+        "items": {
+          "$ref": "#/$defs/PageDialog"
+        },
+        "type": "array"
+      },
+      "type": {
+        "type": "string"
+      }
+    },
+    "title": "Handoff",
+    "type": "object"
+  },
+  "PageDialog": {
+    "additionalProperties": true,
+    "description": "Dialog opened by the page (never accepted by the agent: browser_handle_dialog).",
+    "properties": {
+      "defaultPrompt": {
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      },
+      "tabId": {
+        "type": "integer"
+      },
+      "type": {
+        "type": "string"
+      },
+      "url": {
+        "type": "string"
+      }
+    },
+    "title": "PageDialog",
+    "type": "object"
+  }
+}
    • addedOutput schema / additionalProperties
      Added value: +true
    • addedOutput schema / description
      Added value: +"Whether the user must take over (2FA, CAPTCHA)."
    • addedOutput schema / properties / data
      Added value: +{
+  "$ref": "#/$defs/Handoff"
+}
    • removedOutput schema / properties / result
      Removed value: -{
-  "title": "Result",
-  "type": "string"
-}
    • addedOutput schema / properties / status
      Added value: +{
+  "const": "success",
+  "type": "string"
+}
    • addedOutput schema / properties / untrusted_note
      Added value: +{
+  "description": "Page text that looks like instructions aimed at an AI",
+  "type": "string"
+}
    • addedOutput schema / properties / warning
      Added value: +{
+  "description": "Emergency stop hotkey not held, or similar notice",
+  "type": "string"
+}
    • changedOutput schema / required
      Previous value: -[
-  "result"
-]New value: +[
+  "status",
+  "data"
+]
    • changedOutput schema / title
      Previous value: -"browser_check_handoffOutput"New value: +"HandoffAnswer"
  2. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered structurally. The description adds the specific detection targets (SMS, Google Authenticator, Turnstile), which is genuine value, but never explains that a positive result implies a human handoff is required or that the operation cannot self-resolve a CAPTCHA.

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?

A single front-loaded sentence with no filler or repetition. It is efficient, though the brevity borders on under-specification given the 'handoff' concept is never unpacked.

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?

An output schema exists, so return values need not be explained, and the sole parameter is fully documented in the schema. However, the central term 'handoff' is never defined and no next step is given after a positive detection, which is the one thing an agent must know to use this tool correctly.

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?

Only one parameter (tab_id) at 100% schema description coverage, which already documents its provenance from browser_new_tab / browser_adopt_tab. The description adds no further constraint, such as whether the tab must be focused or active, so the baseline 3 applies.

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?

Names a specific verb (detects) and specific resources (2FA screen, CAPTCHA, Cloudflare Turnstile), so an agent can tell this is a blocker-detection probe rather than an interaction tool. It does not reconcile 'detects' with the name's 'handoff' framing, leaving the terminal concept implicit, but the resource is unambiguous enough to distinguish it from siblings.

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?

'Proactively' is the only usage signal, implying it should be called before/around actions that might hit a wall. There is no guidance on when-not to call it, how it relates to browser_vision_inspect or browser_wait_for, or what the agent should do once a screen is detected.

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