Skip to main content
Glama
NexBrowser MCP Server

NexBrowser MCP Server

Official
by nex-browser

nex_browser_captcha_complete

Completes a prepared CAPTCHA challenge by polling its task status, applying the returned answer or clicking Grid tiles and verify, and handling rejection or expiry with limited retries.

Instructions

Query the task once; on SUCCEEDED apply the answer to the captured widget, or click the returned Grid tiles and the verify button. Poll pending tasks every 3–5 seconds. A changed Grid returns nextPrepareId without charging; submit it as the next round. REJECTED stops automatic new purchases; inspect the site verification response. Repeat calls only inspect progress and never click again. On FAILED/EXPIRED, check billing and prepare a fresh challenge, within 3 attempts. An unclear charge or application blocks new charges. Website acceptance needs page evidence; never clicks the final sign-up/login button.

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": {
      "prepareId": "<prepareId>"
    },
    "name": "nex_browser_captcha_complete"
  }
}

Input Schema

NameRequiredDescriptionDefault
prepareIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2026.10.24

TDQS

A3.7/5.0
Behavior5/5

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

With annotations only declaring readOnlyHint=false and idempotentHint=false, the description carries real weight: it discloses that Grid changes are not charged, that repeat calls are inspection-only and never re-click, that REJECTED halts automatic purchasing, and that an unclear charge blocks new charges. These billing and side-effect traits go well beyond what the structured annotations provide.

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?

The main happy path is front-loaded, which helps, but the remainder is a dense run-on of semicolon-joined fragments ('REJECTED stops automatic new purchases; inspect the site verification response') with no grouping by outcome state. For a one-parameter tool the volume is high, and several clauses ('An unclear charge or application blocks new charges') read as cryptic rather than economical.

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?

There is no output schema, and the description effectively covers the return states (SUCCEEDED, REJECTED, FAILED/EXPIRED, changed Grid returning nextPrepareId), so an agent can anticipate responses. What is missing is the origin and format of the required prepareId and any pointer to which sibling produces it.

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 coverage is 0% and the single parameter prepareId is undocumented in the schema, so the description must compensate. It does add lifecycle meaning indirectly ('A changed Grid returns nextPrepareId without charging; submit it as the next round'), implying prepareId is a round handle that can be replaced, but it never states the format or that it is the identifier produced by the prepare step.

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

Purpose3/5

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

The description conveys that this tool drives a captcha task to completion ('Query the task once; on SUCCEEDED apply the answer to the captured widget, or click the returned Grid tiles and the verify button'), but the core verb is buried in a workflow playbook rather than stated up front. It never plainly distinguishes itself from the nearby siblings nex_browser_captcha_prepare, nex_browser_captcha_submit, nex_captcha_query, and nex_captcha_apply_result, which overlap heavily with the query/apply/click steps described here.

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

Usage Guidelines4/5

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

Conditions are explicit and actionable: poll pending tasks every 3-5 seconds, treat a changed Grid as a no-charge nextPrepareId round, stop on REJECTED, and on FAILED/EXPIRED check billing and prepare fresh within 3 attempts. It also sets a boundary ('never clicks the final sign-up/login button'). The gaps are that no sibling alternative is named (e.g., when to use nex_captcha_query instead) and the 3-attempt ceiling's origin is unclear.

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