AI agents invoke runTest to trigger actions in MCP Frontend Testing Server. 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.
This tool runs test code and triggers external operations (test frameworks), whose effects depend on test arguments and the code being tested. Test execution can have side effects on the system (file I/O, network calls, temporary process creation). The tool cannot be safely classified as Read (it has external effects) or Write (test execution can be more impactful than just modifications).
From the tool's definition Tool name 'runTest' on a frontend testing server explicitly designed for 'test execution'; server description confirms this is a testing framework integration tool for Jest and Cypress
Documented attack patterns abuse exactly the kind of access runTest gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Frontend Testing Server, and nothing reaches the server without passing your rules. This is the rule we recommend for runTest:
{
"version": "1",
"default": "deny",
"tools": {
"runTest": {
"limits": [
{
"counter": "runtest_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}runTest 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.
Free to start. No card required.
runTest. It is categorised as a Execute tool in the MCP Frontend Testing Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Frontend Testing Server MCP server in PolicyLayer and add a rule for runTest: 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 MCP Frontend Testing Server. Nothing to install.
runTest is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the runTest 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.
Set action: deny in the PolicyLayer policy for runTest. 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.
runTest is provided by the MCP Frontend Testing Server MCP server (studentofjs/mcp-frontend-testing). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Frontend Testing Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 MCP Frontend Testing Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.