perform_step · Blop MCP: Risk & Policy

WHAT IT DOES

What perform_step does on Blop

AI agents invoke perform_step to trigger actions in Blop. 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 perform_step needs a policy

The tool performs real browser interactions (clicks, typing, navigation, keypresses) that cause side effects in the browser environment. These actions can trigger form submissions, navigation to pages, UI interactions with real consequences, and more.

From the tool's definition 'click | type | wait | press_key | navigate' — these are browser execution actions that trigger external operations

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

perform_step Rate-limited

perform_step 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": {
    "perform_step": {
      "limits": [
        {
          "counter": "perform_step_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 Blop, so you can run agents against it safely.

FAQ

Questions about perform_step

What does the perform_step tool do? +

One structured step: click | type | wait | press_key | navigate (see PerformStepSpec). It is categorised as a Execute tool in the Blop MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on perform_step? +

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

What risk level is perform_step? +

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

Can I rate-limit perform_step? +

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

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

perform_step is provided by the Blop MCP server (n2400813g/blop-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.