runPercyScan

THE RISK

High Risk

Why runPercyScan needs a policy

This tool triggers an external Percy visual testing operation. While not destructive (scans do not delete data) or financial, it is an Execute category tool because it runs code/triggers external operations. The severity is high because a compromised agent could exhaust testing quotas, consume resources, or generate spurious test results that pollute the build pipeline.

From the tool's definition Tool description states 'Run a Percy visual test scan' — this directly executes an external operation (a visual testing scan) whose effects depend on arguments and cannot be undone without side effects.

Documented attack patterns abuse exactly the kind of access runPercyScan gives an agent:

POLICY

How to control runPercyScan

PolicyLayer is an MCP gateway — it sits between your AI agents and BrowserStack, and nothing reaches the server without passing your rules. This is the rule we recommend for runPercyScan:

policy.json

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

runPercyScan 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.

Create a free account and register BrowserStack — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More BrowserStack tools

Execute runAppLiveSession Use this tool when user wants to manually check their app on a particular mobile device us Execute runAppTestsOnBrowserStack runAppTestsOnBrowserStack Execute runBrowserLiveSession Launch a BrowserStack Live session (desktop or mobile). Execute startAccessibilityScan Start an accessibility scan via BrowserStack and retrieve a local CSV report path. Execute takeAppScreenshot Use this tool to take a screenshot of an app running on a BrowserStack device. This is use Write addPercySnapshotCommands addPercySnapshotCommands Write addTestResult Add a test result to a specific test run via BrowserStack Test Management API. Write createAccessibilityAuthConfig Create an authentication configuration for accessibility scans. Supports both form-based a

All 43 BrowserStack tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

Govern code and CI agents → Branch allowlists, approval on merges, and rate caps on the build and pipeline tools agents trigger.
High-risk tools in BrowserStack → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →
PolicyLayer vs alternatives → How deterministic, per-call MCP policy compares with gateways, identity layers, and authorisation platforms.

FAQ

Questions about runPercyScan

What does the runPercyScan tool do? +

Run a Percy visual test scan. Example prompts : Run this Percy build/scan. Never run percy scan/build without this tool. It is categorised as a Execute tool in the BrowserStack MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on runPercyScan? +

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

What risk level is runPercyScan? +

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

Can I rate-limit runPercyScan? +

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

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

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

Enforce policy on every BrowserStack tool call.

Start from BrowserStack, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →