Skip to main content
Glama

create_task

Solves supported CAPTCHAs, anti-bot challenges, and recognition tasks via CapSolver; submit a task or JSON task file, then use the returned task ID to fetch results.

Instructions

Solve a supported CAPTCHA, anti-bot challenge, or recognition task with CapSolver.

Use this for reCAPTCHA, DataDome and other supported types once the required inputs are available. Provide task OR a local JSON task_file (max 16 MB). Live solves may incur a charge. Supply a stable request_id and reuse it after a lost response. For processing results, use wait_for_result with the task ID. For tasks requiring a proxy, supply its documented fields in the task. Default catalog validation checks the reviewed schema. Use explicit validation=provider only after reading current official docs for a new type or field; this skips local type rules. It never retries another type or downgrades validation automatically.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskNo
app_idNo
task_fileNo
request_idNo
validationNocatalog
callback_urlNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full behavioral burden and does so: live solves may incur a charge, request_id should be stable and reused after a lost response, task_file is capped at 16 MB, and the tool never retries another type or downgrades validation automatically. Those cost, idempotency, and no-fallback semantics are exactly the traits an agent cannot infer from the schema.

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?

Purpose and the primary task/task_file choice are front-loaded, and most sentences carry distinct operational facts. It is somewhat dense and line-broken into fragments, and the validation paragraph could be tightened, but there is no filler or restatement of structured fields.

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 six-parameter, zero-annotation mutation tool this is nearly complete: cost, idempotency, fallback policy, input alternatives, and result-handling routing are all covered, and the existing output schema means return values need not be described. The only real holes are app_id and callback_url, whose purpose (app scoping, async delivery) is left to guesswork.

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 0%, so the description must compensate, and it does for most parameters: task vs. local task_file (with size limit), request_id stability, validation's catalog-vs-provider behavior, and the need to supply documented proxy fields inside task. It leaves app_id and callback_url completely unmentioned, so two of six parameters remain semantically undefined.

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?

Opens with a specific verb and resource: 'Solve a supported CAPTCHA, anti-bot challenge, or recognition task with CapSolver.' It also clarifies that task creation is what initiates the solve, and names a sibling (wait_for_result) as the separate step for retrieving output, so the agent can place this tool in the workflow 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 Guidelines5/5

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

Explicit usage conditions: use it for reCAPTCHA, DataDome and other supported types 'once the required inputs are available', and use wait_for_result with the task ID to process results. It also states a concrete escalation rule for validation=provider (only after reading current official docs for a new type/field) that tells the agent when the default path is wrong.

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