site_run · Ma Browser MCP: Risk & Policy

WHAT IT DOES

What site_run does on Ma Browser

AI agents invoke site_run to trigger actions in Ma Browser. 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 site_run needs a policy

The tool executes site adapters which perform operations on real websites using the user's authenticated browser session. This is an Execute category tool because it triggers external operations whose effects depend on the adapter arguments.

From the tool's definition Tool description states 'Run a site adapter' - the word 'Run' indicates execution of code/operations. Server description confirms it 'lets AI agents use your real browser as an API, accessing any website with your login state', meaning the tool executes…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

site_run Rate-limited

site_run 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": {
    "site_run": {
      "limits": [
        {
          "counter": "site_run_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 Ma Browser, so you can run agents against it safely.

FAQ

Questions about site_run

What does the site_run tool do? +

Run a site adapter and return its structured data. It is categorised as a Execute tool in the Ma Browser MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on site_run? +

Register the Ma Browser MCP server in PolicyLayer and add a rule for site_run: 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 Ma Browser. Nothing to install.

What risk level is site_run? +

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

Can I rate-limit site_run? +

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

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

site_run is provided by the Ma Browser MCP server (zzhan111/multi-agents-browser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

site_run is one line of Ma Browser's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →