Run performance benchmarks using pytest-benchmark with statistical analysis
AI agents invoke python_benchmark to trigger actions in MCP DevTools 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 executes code (via pytest-benchmark) whose effects depend on the benchmark arguments provided. While benchmarking is typically non-destructive, the execution of arbitrary benchmark code could have side effects depending on what is being benchmarked (file I/O, network calls, resource consumption).
From the tool's definition The tool description states it will 'Run performance benchmarks using pytest-benchmark with statistical analysis.' The verb 'Run' indicates code execution.
Documented attack patterns abuse exactly the kind of access python_benchmark gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP DevTools Server, and nothing reaches the server without passing your rules. This is the rule we recommend for python_benchmark:
{
"version": "1",
"default": "deny",
"tools": {
"python_benchmark": {
"limits": [
{
"counter": "python_benchmark_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}python_benchmark 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.
Run performance benchmarks using pytest-benchmark with statistical analysis. It is categorised as a Execute tool in the MCP DevTools Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP DevTools Server MCP server in PolicyLayer and add a rule for python_benchmark: 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 DevTools Server. Nothing to install.
python_benchmark 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 python_benchmark 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 python_benchmark. 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.
python_benchmark is provided by the MCP DevTools Server MCP server (rshade/mcp-devtools-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP DevTools 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.
79 MCP DevTools Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.