Low Risk

dependency_tree

Display dependency tree (provide either cwd path or package.json content)

How to control dependency_tree ↓

What dependency_tree does on Npmplus

AI agents call dependency_tree to retrieve information from Npmplus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why dependency_tree needs a policy

This tool queries and presents the hierarchical structure of project dependencies without creating, modifying, deleting, or executing any code. It is a pure introspection mechanism analogous to listing or fetching data. The low severity reflects minimal blast radius—misuse yields only information disclosure about the dependency graph, not system or data harm.

From the tool's definition Tool name 'dependency_tree' and description 'Display dependency tree' indicate a retrieval/query operation with no modification of state. The verb 'Display' and the read-only nature of examining package dependencies confirm this is informational.

Documented attack patterns abuse exactly the kind of access dependency_tree gives an agent:

How to control dependency_tree

PolicyLayer is an MCP gateway — it sits between your AI agents and Npmplus, and nothing reaches the server without passing your rules. This is the rule we recommend for dependency_tree:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "dependency_tree": {}
  }
}

dependency_tree is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Npmplus — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about dependency_tree

What does the dependency_tree tool do? +

Display dependency tree (provide either cwd path or package.json content). It is categorised as a Read tool in the Npmplus MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on dependency_tree? +

Register the Npmplus MCP server in PolicyLayer and add a rule for dependency_tree: 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 Npmplus. Nothing to install.

What risk level is dependency_tree? +

dependency_tree is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit dependency_tree? +

Yes. Add a rate_limit block to the dependency_tree 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.

How do I block dependency_tree completely? +

Set action: deny in the PolicyLayer policy for dependency_tree. 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.

What MCP server provides dependency_tree? +

dependency_tree is provided by the Npmplus MCP server (shacharsol/js-package-manager-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Npmplus tool call.

Start from Npmplus, 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.

16 Npmplus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.