This record as markdown: /tools/io-github-dave-london-npm/package-resolve.md
What package-resolve does on Npm
AI agents invoke package-resolve 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 package-resolve is rated High
Resolving Swift package dependencies is not a pure read operation; it involves executing the Swift Package Manager resolver, which fetches packages from remote sources and modifies local dependency caches. This constitutes an Execute-level action. The severity is medium because while it can trigger external network calls and filesystem changes, it is generally reversible and scoped to the project environment.
From the tool's definition 'Resolves Swift package dependencies' — dependency resolution triggers external network operations and filesystem modifications (fetching and caching packages)
Attacks that exploit this kind of access
The rule that runs package-resolve 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 package-resolve, this is the rule to start with:
package-resolve 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 package-resolve call is checked against it from then on.
Questions about package-resolve
Resolves Swift package dependencies and returns structured resolution results. 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 package-resolve: 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.
package-resolve 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 package-resolve 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 package-resolve. 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.
package-resolve 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