explore

THE RISK

Low Risk

Why explore needs a policy

This tool retrieves and displays folder/file metadata and hierarchy without any side effects. It is analogous to Read operations (list, get) and presents no risk of data modification, deletion, or code execution. The low severity reflects minimal blast radius—worst case reveals directory structure an AI agent already has filesystem access to explore.

From the tool's definition Tool name 'explore' and description 'Explore folder structure with ls-like navigation showing both directories and files' indicates read-only directory listing functionality similar to the 'ls' command.

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

POLICY

How to control explore

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

policy.json

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

explore 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 Folder — 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 Folder tools

Read find_documents Find documents using document-level embeddings for topic discovery. Returns ranked documen Read get_chunks Retrieve specific chunks by ID for targeted content access Read get_document_metadata Get document metadata and structure with chunk navigation from a specific folder Read get_document_text Get extracted plain text from any document type with character-based pagination Read get_server_info Get information about the folder-mcp server and daemon status Read list_documents List documents in a specific folder Read list_folders List all configured folders in the multi-folder system Read search_content Search for content using hybrid semantic and exact term matching. Combines vector similari

All 9 Folder 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 explore

What does the explore tool do? +

Explore folder structure with ls-like navigation showing both directories and files. It is categorised as a Read tool in the Folder MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on explore? +

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

What risk level is explore? +

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

Can I rate-limit explore? +

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

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

explore is provided by the Folder MCP server (okets/folder-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Folder tool call.

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

CHECK YOUR STACK →