This record as markdown: /tools/io-github-dave-london-build/gradle-test.md
What gradle-test does on Build
AI agents invoke gradle-test to trigger actions in Build. 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.
Why gradle-test is rated High
Gradle test execution runs arbitrary project code and test suites on the host system. While typically used for testing, it can trigger side effects, consume resources, and execute arbitrary code defined in build scripts. The incomplete description lowers confidence slightly, but the name combined with the build-tool server context strongly implies code execution.
From the tool's definition Tool name 'gradle-test' and server context 'build tool' — runs Gradle test tasks, which executes code in the project environment. Description is truncated/uninformative ('Runs' only).
Attacks that exploit this kind of access
The rule that runs gradle-test safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Build, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For gradle-test, this is the rule to start with:
gradle-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.
The button opens the PolicyLayer dashboard: create your workspace, connect Build, apply this rule, and every gradle-test call is checked against it from then on.
Questions about gradle-test
Runs. It is categorised as a Execute tool in the Build MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Build MCP server in PolicyLayer and add a rule for gradle-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 Build. Nothing to install.
gradle-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 gradle-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 gradle-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.
gradle-test is provided by the Build MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Build, and thousands of servers like it.
Across the catalogue