This record as markdown: /tools/io-github-portel-dev-ncp/install.md
What install does on Ncp
AI agents invoke install to trigger actions in Ncp. 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 install is rated High
Installing npm packages executes package manager commands that download and run arbitrary code on the system, modify the filesystem, and can introduce malicious dependencies. This is an Execute-category action with high severity because an AI agent could be manipulated into installing malicious or unwanted packages.
From the tool's definition "Install npm packages" — installs software packages into the environment
Attacks that exploit this kind of access
The rule that runs install safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ncp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For install, this is the rule to start with:
install 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 Ncp, apply this rule, and every install call is checked against it from then on.
Questions about install
Install npm packages. It is categorised as a Execute tool in the Ncp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ncp MCP server in PolicyLayer and add a rule for install: 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 Ncp. Nothing to install.
install 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 install 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 install. 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.
install is provided by the Ncp MCP server (@portel/ncp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ncp, and thousands of servers like it.
This server
Across the catalogue