purroxy_run_capability · Purroxy MCP: Risk & Policy

WHAT IT DOES

What purroxy_run_capability does on Purroxy

AI agents invoke purroxy_run_capability to trigger actions in Purroxy. 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 purroxy_run_capability needs a policy

This tool runs pre-recorded browser automation routines, which constitutes executing external operations whose effects depend on the capability argument passed. While the capabilities are 'recorded' (suggesting some pre-authorization), the tool itself is an Execute primitive that triggers side effects in a browser context.

From the tool's definition Tool description states 'Execute a recorded browser automation capability by name.' The verb 'Execute' directly indicates code/automation execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

purroxy_run_capability Rate-limited

purroxy_run_capability 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": {
    "purroxy_run_capability": {
      "limits": [
        {
          "counter": "purroxy_run_capability_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 Purroxy, so you can run agents against it safely.

FAQ

Questions about purroxy_run_capability

What does the purroxy_run_capability tool do? +

Execute a recorded browser automation capability by name. It is categorised as a Execute tool in the Purroxy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on purroxy_run_capability? +

Register the Purroxy MCP server in PolicyLayer and add a rule for purroxy_run_capability: 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 Purroxy. Nothing to install.

What risk level is purroxy_run_capability? +

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

Can I rate-limit purroxy_run_capability? +

Yes. Add a rate_limit block to the purroxy_run_capability 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 purroxy_run_capability completely? +

Set action: deny in the PolicyLayer policy for purroxy_run_capability. 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 purroxy_run_capability? +

purroxy_run_capability is provided by the Purroxy MCP server (kuvopllc/purroxy2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.