AI agents use upgrade_packages to create or update resources in NPM Helper MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your NPM Helper MCP environment.
This tool writes changes to package.json by upgrading dependency versions. While package.json modifications are technically reversible (via version control), this is a Write operation with high severity because incorrect upgrades can break the entire project, introduce breaking changes, or create dependency conflicts across a codebase.
From the tool's definition 'Upgrade dependencies in package.json' — modifies the package.json file by changing dependency versions
Documented attack patterns abuse exactly the kind of access upgrade_packages gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and NPM Helper MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for upgrade_packages:
{
"version": "1",
"default": "deny",
"tools": {
"upgrade_packages": {
"limits": [
{
"counter": "upgrade_packages_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}upgrade_packages stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Upgrade dependencies in package.json. It is categorised as a Write tool in the NPM Helper MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the NPM Helper MCP server in PolicyLayer and add a rule for upgrade_packages: 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 Helper MCP. Nothing to install.
upgrade_packages is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the upgrade_packages 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 upgrade_packages. 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.
upgrade_packages is provided by the NPM Helper MCP server (pinkpixel-dev/npm-helper-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from NPM Helper MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 NPM Helper MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.