solve_captcha · Mcp Web MCP: Risk & Policy

WHAT IT DOES

What solve_captcha does on Mcp Web

AI agents invoke solve_captcha to trigger actions in Mcp Web. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why solve_captcha needs a policy

This tool actively interacts with an external CAPTCHA challenge system by submitting answers, triggering an external operation (CAPTCHA resolution) that enables continued web access. It goes beyond reading data — it executes an action against an external service. Misuse could enable automated bypassing of bot-detection mechanisms, potentially violating terms of service or enabling scraping at scale.

From the tool's definition Solves a CAPTCHA challenge by providing the indices of images containing the requested object

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

solve_captcha Rate-limited

solve_captcha stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "solve_captcha": {
      "limits": [
        {
          "counter": "solve_captcha_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mcp Web, so you can run agents against it safely.

FAQ

Questions about solve_captcha

What does the solve_captcha tool do? +

Solves a CAPTCHA challenge by providing the indices of images containing the requested object. It is categorised as a Execute tool in the Mcp Web MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on solve_captcha? +

Register the Mcp Web MCP server in PolicyLayer and add a rule for solve_captcha: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Web. Nothing to install.

What risk level is solve_captcha? +

solve_captcha is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit solve_captcha? +

Yes. Add a rate_limit block to the solve_captcha rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block solve_captcha completely? +

Set action: deny in the PolicyLayer policy for solve_captcha. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides solve_captcha? +

solve_captcha is provided by the Mcp Web MCP server (tsfreddie/mcp-web). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.