Skip to main content
Glama
NexBrowser MCP Server

NexBrowser MCP Server

Official
by nex-browser

nex_captcha_buy

Destructive

Creates a NexCaptcha recognition task for browser-integrated workflows and charges the account at the current server price; it does not submit to the target website.

Instructions

Create a NexCaptcha recognition task for standalone or agent-driven browser integration, using actual inputs matching the current online schema (adapter, no platform API keys). This is the charging entry for the agent-driven flow; it never submits to the website. For a page, prefer free nex_captcha_detect, confirm a permitted application capability, and pass workflow=BROWSER_RESULT. Never omit schema-required inputs, guess values or switch to GRID to evade a failure. Enterprise s may be omitted when unsupported by the online schema; website acceptance is not guaranteed. The fixed Desktop prepare/submit/complete bridge remains optional. The online contract is rechecked before charging. Keep the local id and query it; never repeat a create after an unclear outcome. Charges the balance at the current server price; call it directly when the user's task needs it (a price inquiry is not a purchase request). If the outcome is unclear, reconcile records and billing before any retry. At most 3 attempts per resource flow.

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": {
      "productCode": "<productCode>",
      "adapter": "<adapter>"
    },
    "name": "nex_captcha_buy"
  }
}

Input Schema

NameRequiredDescriptionDefault
adapterYes
workflowNo
productCodeYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2026.11.3
    • addedInput schema / properties / workflow
      Added value: +{
      +  "enum": [
      +    "HTTP_SUBMIT",
      +    "BROWSER_RESULT",
      +    "BROWSER_INTERACTION"
      +  ],
      +  "type": "string"
      +}
  2. Addedv2026.10.24

TDQS

A4.2/5.0
Behavior4/5

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

Goes well beyond the destructiveHint/idempotentHint=false annotations by disclosing that balance is charged at the current server price, that the online contract is rechecked before charging, that website acceptance is not guaranteed, that it never submits to the site, and that records and billing should be reconciled after an unclear outcome. The one gap is that return content (e.g. the task id it says to keep) is only implied.

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

Conciseness3/5

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

Front-loads the key identity and billing warning, which is good, but the prose is dense and repetitive: the unclear-outcome/reconcile instruction appears twice in different sentences, and fragments like 'Enterprise s may be omitted' and 'The fixed Desktop prepare/submit/complete bridge remains optional' read as boilerplate that slows comprehension.

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 paid, non-idempotent create tool with no output schema and a nested adapter object, it covers the important ground: cost model, schema-contract revalidation, retry ceiling, and where to get valid inputs. Only the return value and the meaning of productCode are left thin.

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% across three parameters, so the description must carry the load: it explains that adapter takes actual inputs matching the online schema with no platform API keys, and that workflow=BROWSER_RESULT is the expected value for pages. However productCode is never explained, the workflow enum values are not differentiated, and it defers input details to nex_captcha_product_schema rather than documenting them.

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 specific verb and resource ('Create a NexCaptcha recognition task') and immediately scopes it: it is the charging entry for the agent-driven flow and 'never submits to the website.' It also contrasts itself with the free detect sibling and the optional Desktop prepare/submit/complete bridge, so the agent can separate it from near-neighbors without opening schemas.

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?

Gives explicit alternatives and preconditions: 'prefer free nex_captcha_detect, confirm a permitted application capability, and pass workflow=BROWSER_RESULT,' plus exclusions such as never switching to GRID to evade a failure and never re-creating after an unclear outcome. It also clarifies the trigger ('call it directly when the user's task needs it (a price inquiry is not a purchase request)') and caps retries at 3 per resource 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