webSearch

THE RISK

Low Risk

Why webSearch needs a policy

This tool performs a read-only operation: searching and retrieving publicly available web content. It has no side effects on data or systems, poses minimal security risk even if misused (worst case: retrieving unintended public information), and aligns with the 'Read' category definition for retrieval without side effects.

From the tool's definition Tool description states 'Search the web using DuckDuckGo and retrieve content from search results' — a query and retrieval operation with no modification of data or external state.

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

POLICY

How to control webSearch

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

policy.json

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

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

Create a free account and register Apple MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Apple MCP tools

Execute maps Search locations, manage guides, save favorites, and get directions using Apple Maps Write calendar Search, create, and open calendar events in Apple Calendar app Write mail Interact with Apple Mail app - read unread emails, search emails, and send emails Write messages Interact with Apple Messages app - send, read, schedule messages and check unread messages Write notes Search, retrieve and create notes in Apple Notes app Write reminders Search, create, and open reminders in Apple Reminders app Read contacts Search and retrieve contacts from Apple Contacts app

All 8 Apple MCP tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about webSearch

What does the webSearch tool do? +

Search the web using DuckDuckGo and retrieve content from search results. It is categorised as a Read tool in the Apple MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on webSearch? +

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

What risk level is webSearch? +

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

Can I rate-limit webSearch? +

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

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

webSearch is provided by the Apple MCP server (jxnl/apple-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Apple MCP tool call.

Start from Apple MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →