Skip to main content
Glama

Solve Yandex SmartCaptcha

capskip_solve_yandex_smart

Solve a Yandex SmartCaptcha using a sitekey and page URL and return a valid token for the form's hidden smart-token field. Submit the token once within five minutes.

Instructions

Solve a Yandex SmartCaptcha (a widget loaded from smartcaptcha.yandexcloud.net, usually a ) and get its token. Requires sitekey and url. You do not need to tick the checkbox or answer the challenges it shows; CapSkip returns only the finished token. Put the token in the form's hidden smart-token field, then submit the form. A token is valid for five minutes and can be checked once.

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": {
      "sitekey": "<sitekey>",
      "url": "<url>"
    },
    "name": "capskip_solve_yandex_smart"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesFull URL of the page the captcha appears on, including scheme.
proxyNoSolve from this network. Yandex scores the network every check comes from, so many solves from one address are what makes it ask for harder challenges.
sitekeyYesThe SmartCaptcha sitekey, usually starting with 'ysc1_'. Read it from the data-sitekey of the <div class="smart-captcha"> container, from the sitekey the page passes to window.smartCaptcha.render, or from the sitekey= parameter in the address of the widget iframe on smartcaptcha.yandexcloud.net. Copy it exactly.
timeoutNoSeconds to wait before giving up. Maximum 600.
userAgentNoThe User-Agent to present to Yandex. Usually leave it out.

Output Schema

NameRequiredDescriptionDefault
codeYes
tokenYes
captchaIdYes
solveSecondsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.7.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only tell the agent it is a non-read-only, open-world, non-destructive call; the description adds genuinely new behavior: no checkbox interaction is required, only the finished token is returned, the token is valid five minutes, and it "can be checked once." The single-use/five-minute constraint is the kind of detail that changes how an agent sequences the solve with form submission. It does not cover failure modes, credit cost, or what happens on timeout.

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

Conciseness5/5

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

Purpose and required inputs are front-loaded, followed by the no-interaction clarification, the placement instruction, and the token lifetime. Every sentence carries operational information; the parenthetical widget marker is dense but directly useful for locating the sitekey.

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?

With an output schema present, the description needn't describe the return payload, and it correctly focuses on the surrounding workflow. It covers inputs, expected interaction, and token lifecycle, which is most of what an agent needs. It omits error/timeout behavior and any note on solve cost, which would round out a paid, open-world call.

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 100% and the nested proxy object is documented in-schema with its enum and network-scoring rationale, so the schema already carries parameter meaning. The description only restates that sitekey and url are required, adding no format or interpretation detail beyond that. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

The description opens with a specific verb+resource ("Solve a Yandex SmartCaptcha") and states the deliverable ("get its token"). It even identifies the concrete widget markers (smartcaptcha.yandexcloud.net, `<div class="smart-captcha" data-sitekey="ysc1_...">`), which lets an agent distinguish this from the other captcha siblings without opening a schema.

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?

It gives clear preconditions ("Requires sitekey and url") and an explicit post-condition workflow: put the token in the form's hidden smart-token field, then submit. It also rules out a wrong approach ("You do not need to tick the checkbox or answer the challenges"). It stops short of naming when to pick a different captcha solver, though the per-vendor naming makes the choice largely self-evident.

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