browser_solve_captcha · MCProxy MCP: Risk & Policy

WHAT IT DOES

What browser_solve_captcha does on MCProxy

AI agents invoke browser_solve_captcha to trigger actions in MCProxy. 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 browser_solve_captcha needs a policy

This tool executes an action in a headless browser by submitting a CAPTCHA solution, which triggers an external operation (bypassing bot-detection mechanisms on remote websites). It doesn't merely read data—it actively interacts with and manipulates a web session's state.

From the tool's definition Submit a CAPTCHA solution... analyze the screenshot from browser_check_captcha or browser_navigate, then provide the solution text here

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_solve_captcha Rate-limited

browser_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": {
    "browser_solve_captcha": {
      "limits": [
        {
          "counter": "browser_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 MCProxy, so you can run agents against it safely.

FAQ

Questions about browser_solve_captcha

What does the browser_solve_captcha tool do? +

Submit a CAPTCHA solution. For image CAPTCHAs, analyze the screenshot from browser_check_captcha or browser_navigate, then provide the solution text here. It is categorised as a Execute tool in the MCProxy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_solve_captcha? +

Register the MCProxy MCP server in PolicyLayer and add a rule for browser_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 MCProxy. Nothing to install.

What risk level is browser_solve_captcha? +

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

Can I rate-limit browser_solve_captcha? +

Yes. Add a rate_limit block to the browser_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 browser_solve_captcha completely? +

Set action: deny in the PolicyLayer policy for browser_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 browser_solve_captcha? +

browser_solve_captcha is provided by the MCProxy MCP server (saladtechnologies/mcproxy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.