AI agents invoke go_test 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 runs Go tests, which involves executing arbitrary code in the project. While tests are typically read-only in intent, they execute real code that can have side effects depending on what the tests do. Race detection involves running concurrent code. The blast radius is medium since tests could invoke destructive operations, make network calls, or modify state depending on the test suite.
From the tool's definition "Run Go tests with coverage and race detection" — executes test code in the Go runtime environment
Documented attack patterns abuse exactly the kind of access go_test 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_test:
{
"version": "1",
"default": "deny",
"tools": {
"go_test": {
"limits": [
{
"counter": "go_test_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}go_test 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 tests with coverage and race detection. 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_test: 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_test 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_test 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_test. 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_test 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.