find

SERVERNcp SOURCE@portel/ncp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-portel-dev-ncp/find.md

WHAT IT DOES

What find does on Ncp

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

RISK

Why find is rated Low

This is a read-only search and discovery tool that retrieves information about installed skills at various detail levels. It has no side effects, does not execute operations, and does not modify or delete data. The progressive disclosure mechanism is a retrieval feature, not a capability to perform actions. Low severity due to minimal blast radius—worst case is information disclosure about available skills.

From the tool's definition Tool description states 'Search and discover installed Anthropic Agent Skills' and 'Use depth parameter for progressive disclosure' with increasing detail levels (metadata, documentation, file listings).

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs find 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 find, this is the rule to start with:

find Allowed

find is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "find": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Ncp, apply this rule, and every find call is checked against it from then on.

FAQ

Questions about find

What does the find tool do? +

Search and discover installed Anthropic Agent Skills with progressive detail levels. Use depth parameter for progressive disclosure: 1=metadata only, 2=+SKILL.md content (AI learns skill), 3=+file listings. It is categorised as a Read tool in the Ncp MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on find? +

Register the Ncp MCP server in PolicyLayer and add a rule for find: 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.

What risk level is find? +

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

Can I rate-limit find? +

Yes. Add a rate_limit block to the find 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 find completely? +

Set action: deny in the PolicyLayer policy for find. 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 find? +

find 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.

KEEP EXPLORING

More on Ncp, and thousands of servers like it.

This server

All 275 Ncp tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →