Skip to main content
Glama
NexBrowser MCP Server

NexBrowser MCP Server

Official
by nex-browser

nex_captcha_detect

Read-onlyIdempotent

Detects reCAPTCHA v2/enterprise and Turnstile from supplied HTML or product code, parses locally, and returns integration and purchase guidance for applying results.

Instructions

Free, no purchase: plan agent integration for any enabled product using its current online schema, result contract and workflowGuide. Pass actual url, productCode and adapter; HTML is optional for explicit integration, including text answers, image coordinates and future products. Set workflow when needed and canApply=true only after verifying permitted tools can apply this result in the original page/frame (fill/click need no JavaScript permission). Without productCode, current HTML enables shortcut detection of reCAPTCHA v2/enterprise and Turnstile; HTML is parsed locally, never executed or sent to the solver. Captured observations are checked for conflicts. A missing fixed bridge or generated token script does not make a product unsupported. Missing required inputs, undocumented contracts and unavailable execution capabilities block purchase. Enterprise s is optional when unsupported by the online schema. Use returned nex_captcha_buy arguments, query the local id and apply the documented result with permitted tools; nex_captcha_apply_result is an optional token helper. Never guess inputs or bypass disabled permissions.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "nex_captcha_detect"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
htmlNo
adapterNo
canApplyNo
workflowNo
productCodeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2026.11.3

TDQS

C2/5.0
Behavior3/5

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

The description adds significant value by clarifying that 'HTML is parsed locally, never executed or sent to the solver,' which is a critical behavioral trait not covered by the readOnlyHint annotation. However, this critical info is buried within dense, complex prose.

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

Conciseness1/5

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

The definition is overly verbose and densely packed with internal product language, making it unreadable. It is structured like a multi-page technical manual rather than a concise instruction set for an AI agent.

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

Completeness2/5

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

Given the high complexity and zero schema coverage, the tool attempts to be complete by listing all constraints. However, the use of impenetrable internal jargon prevents the agent from successfully leveraging this information for decision-making or accurate parameter passing.

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

Parameters1/5

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

Since schema description coverage is 0%, the description must define the parameters, but it fails drastically. It lists `url`, `productCode`, and `adapter` but uses non-descriptive technical language without explaining the required format or content for the `adapter` object, rendering it unhelpful.

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

Purpose2/5

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

The description states the tool is for 'plan agent integration' and detection of specific captcha types like reCAPTCHA v2, but this is highly technical jargon. It does not provide a clear, simple statement of the tool's core function for an end-user or general agent.

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

Usage Guidelines2/5

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

While it advises setting parameters like `productCode` and warns never to bypass disabled permissions, it fails to provide contextual guidance on when to use this tool over siblings like `nex_browser_get_text` or `nex_captcha_query`. The usage advice is focused on system constraints rather than operational flow.

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