This record as markdown: /tools/io-github-dave-london-npm/vet.md
What vet does on Npm
AI agents invoke vet to trigger actions in Npm. 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 vet is rated High
The tool executes the 'go vet' command against code, which runs external static analysis tooling. While read-like in intent (analyzing code), it actively executes a process/command on the system, classifying it as Execute. Severity is medium since it runs code analysis tools that could potentially be pointed at arbitrary code paths, but has limited write or destructive capability.
From the tool's definition Runs go vet and returns structured static analysis diagnostics with analyzer names. Uses -json flag for native JSON output with automatic text fallback.
Attacks that exploit this kind of access
The rule that runs vet safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Npm, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For vet, this is the rule to start with:
vet 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 Npm, apply this rule, and every vet call is checked against it from then on.
Questions about vet
Runs go vet and returns structured static analysis diagnostics with analyzer names. Uses -json flag for native JSON output with automatic text fallback. It is categorised as a Execute tool in the Npm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Npm MCP server in PolicyLayer and add a rule for vet: 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 Npm. Nothing to install.
vet 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 vet 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 vet. 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.
vet is provided by the Npm 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 Npm, and thousands of servers like it.
This server
Across the catalogue