This record as markdown: /tools/io-github-dave-london-docker/test.md
What test does on Docker
AI agents invoke test to trigger actions in Docker. 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 test is rated High
The description is truncated to a single word 'Runs', which strongly implies execution of some command or process. In a Docker/build toolchain context (alongside tools like build, ansible-playbook, bazel), a 'test' tool that 'Runs' almost certainly executes commands inside containers or as part of a build pipeline.
From the tool's definition Tool name 'test' with description 'Runs' (truncated/uninformative). In a Docker context, 'test' likely executes test commands or scripts inside containers.
Attacks that exploit this kind of access
The rule that runs test safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Docker, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For test, this is the rule to start with:
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 Docker, apply this rule, and every test call is checked against it from then on.
Questions about test
Runs. It is categorised as a Execute tool in the Docker MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Docker MCP server in PolicyLayer and add a rule for 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 Docker. Nothing to install.
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 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 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.
test is provided by the Docker MCP server (@paretools/docker). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Docker, and thousands of servers like it.
Across the catalogue