This record as markdown: /tools/io-github-portel-dev-ncp/up.md
What up does on Ncp
AI agents invoke up 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 up is rated High
This tool triggers external operations (cloud infrastructure deployment) whose effects depend on the Pulumi configuration and state. While not immediately destructive, deployment operations can create, modify, or remove cloud resources with significant blast radius. Classified as Execute rather than Write because it invokes an external orchestration engine with complex, environment-dependent side effects.
From the tool's definition Tool name 'up' and description 'Deploy Pulumi stack' indicate execution of infrastructure deployment operations. Pulumi is an infrastructure-as-code framework that executes real-world changes to cloud resources.
Attacks that exploit this kind of access
The rule that runs up 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 up, this is the rule to start with:
up 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 up call is checked against it from then on.
Questions about up
Deploy Pulumi stack. 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 up: 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.
up 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 up 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 up. 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.
up 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