This record as markdown: /tools/io-github-dave-london-npm/restore.md
What restore does on Npm
AI agents invoke restore 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 restore is rated High
This tool executes an external CLI command (dotnet restore) that downloads and installs package dependencies from remote sources. While it is a common development operation and largely reversible, it triggers external network operations and writes files to disk, making it an Execute-category action.
From the tool's definition 'Runs dotnet restore to restore NuGet dependencies' — executes a dotnet CLI command to fetch and install NuGet packages
Attacks that exploit this kind of access
The rule that runs restore 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 restore, this is the rule to start with:
restore 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 restore call is checked against it from then on.
Questions about restore
Runs dotnet restore to restore NuGet dependencies and returns structured 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 restore: 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.
restore 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 restore 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 restore. 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.
restore 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