AI agents invoke filter_updates to trigger actions in NPM Helper MCP. 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.
The description is ambiguous ('Check/upgrade'), but the 'upgrade' aspect implies it can modify the project's installed packages, not merely read. Upgrading dependencies is a Write/Execute action that changes the project state.
From the tool's definition 'Check/upgrade updates for specific packages' — the tool both checks AND upgrades packages, meaning it can actively modify installed dependencies
Documented attack patterns abuse exactly the kind of access filter_updates 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 filter_updates:
{
"version": "1",
"default": "deny",
"tools": {
"filter_updates": {
"limits": [
{
"counter": "filter_updates_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} filter_updates 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.
Free to start. No card required.
Check/upgrade updates for specific packages. It is categorised as a Execute tool in the NPM Helper MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the NPM Helper MCP server in PolicyLayer and add a rule for filter_updates: 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.
filter_updates 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 filter_updates 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 filter_updates. 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.
filter_updates 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.