Run Go benchmarks to measure code performance
AI agents invoke go_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 Go benchmark code, which is a form of code execution. While benchmarks are typically read-only in terms of side effects, they still involve running code that could potentially consume resources, fail unexpectedly, or trigger unintended behavior in the codebase.
From the tool's definition Tool description states 'Run Go benchmarks' which invokes execution of code via the Go benchmark system. Benchmarking requires executing arbitrary code and measuring performance, making it an Execute operation that runs code whose effects depend on the…
Documented attack patterns abuse exactly the kind of access go_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 go_benchmark:
{
"version": "1",
"default": "deny",
"tools": {
"go_benchmark": {
"limits": [
{
"counter": "go_benchmark_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}go_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 Go benchmarks to measure code performance. 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 go_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.
go_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 go_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 go_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.
go_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.