Skip to main content
Glama

Solve GeeTest v4

capskip_solve_geetest_v4

Solve GeeTest v4 captchas from just a captcha_id and page URL, returning the five values (lot_number, pass_token, gen_time, captcha_output, captcha_id) needed to complete the site's verification request.

Instructions

Solve a GeeTest v4 captcha (a page loading static.geetest.com/v4/gt4.js and calling initGeetest4) and get the five values the site verifies: captcha_id, lot_number, pass_token, gen_time and captcha_output. Requires captcha_id and url only; unlike GeeTest v3 there is no challenge to fetch first. Every v4 challenge type is answered (slide, icon, nine-grid, match and the rest). Send the five values under those same names in the request the page's own submit makes. For GeeTest v3 (gt + challenge) use capskip_solve_geetest instead.

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": {
      "captcha_id": "<captcha_id>",
      "url": "<url>"
    },
    "name": "capskip_solve_geetest_v4"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesFull URL of the page the captcha appears on, including scheme.
proxyNoSolve through this proxy so the answer is produced from its IP.
timeoutNoSeconds to wait before giving up. Maximum 600.
risk_typeNoChallenge type to ask GeeTest for: 'slide', 'icon', 'nine', 'word', 'phrase', 'match', 'winlinze', 'svg_seed', 'svg_icon' or 'ai'. GeeTest applies it only where the site allows it. Usually leave it out: the site's own choice wins and every type is solved.
captcha_idYesThe GeeTest v4 captcha_id: 32 hex characters, the same for every visitor. The page loads static.geetest.com/v4/gt4.js and passes it to initGeetest4 as captchaId; if the call is built at runtime, it is the captcha_id parameter of the request to gcaptcha4.geetest.com/load.

Output Schema

NameRequiredDescriptionDefault
codeYes
gen_timeNo
captchaIdYes
isOfflineNo
captcha_idNo
lot_numberNo
pass_tokenNo
solveSecondsYes
captcha_outputNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.7.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare openWorldHint=true and readOnlyHint=false, but the description adds real behavioral context beyond them: no pre-fetch/challenge handshake, coverage of every v4 challenge type, and where the answer must be delivered (the page's own submit, under the same five names). It does not discuss cost, latency, or failure modes beyond the timeout already documented in the schema, so it is not exhaustive.

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?

Front-loaded with the action and the five returned values, then the requirements, then the sibling routing — well ordered. Minor redundancy in stating the five values twice (once as outputs, once as what to submit), though the repetition serves a distinct delivery instruction.

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

Completeness5/5

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 need not detail return shape, yet it names the five values anyway for the delivery step. For a tool with proxy, timeout, risk_type options and a v3 sibling, every decision an agent must make is covered.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds the semantic that only captcha_id and url matter and that the v3-style challenge parameter does not exist for v4 — a non-obvious expectation-defining detail. The captcha_id format and discovery path are largely restated from the schema, limiting further credit.

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 ("Solve a GeeTest v4 captcha") and pins down the exact scope by naming the five verified outputs (captcha_id, lot_number, pass_token, gen_time, captcha_output) and the page signature (static.geetest.com/v4/gt4.js, initGeetest4). It explicitly distinguishes itself from capskip_solve_geetest (v3), so an agent can route without opening either schema.

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 the when-to-use condition plus the exclusions: "Requires captcha_id and url only; unlike GeeTest v3 there is no challenge to fetch first", and "For GeeTest v3 (gt + challenge) use capskip_solve_geetest instead." It even explains how to obtain captcha_id at runtime, leaving nothing to inference.

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