Low Risk

find_places

Search for public facilities in Seoul (restrooms, pharmacies, WiFi hotspots, AED locations, tourist info centers). Args: type: Type of facility — "toilet", "pharmacy", "wifi", "aed", or "tourist_info". district: Seoul district name in English or Korean (e.g., "gangnam", "jongno", "강남구", "종로구"). f...

Part of the Seoul Essentials server.

find_places is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE SEOUL ESSENTIALS →

Free to start. No card required.

AI agents call find_places to retrieve information from Seoul Essentials without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though find_places only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

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

See the full Seoul Essentials policy for all 4 tools.

Get this rule live on your own Seoul Essentials server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY SEOUL ESSENTIALS →

These attack patterns abuse exactly the kind of access find_places gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so find_places only ever does what you allow.

SECURE SEOUL ESSENTIALS →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the find_places tool do? +

Search for public facilities in Seoul (restrooms, pharmacies, WiFi hotspots, AED locations, tourist info centers). Args: type: Type of facility — "toilet", "pharmacy", "wifi", "aed", or "tourist_info". district: Seoul district name in English or Korean (e.g., "gangnam", "jongno", "강남구", "종로구"). filters: Service-specific filters as key-value pairs. Examples: {"english": true} for pharmacies with English support, {"is_24h": true} for 24-hour restrooms, {"indoor": true} for indoor WiFi. limit: Maximum number of results to return (1-50, default 10). Returns: A list of matching places with location, services, and hours information.. It is categorised as a Read tool in the Seoul Essentials MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on find_places? +

Register the Seoul Essentials MCP server in PolicyLayer and add a rule for find_places: 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 Seoul Essentials. Nothing to install.

What risk level is find_places? +

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

Can I rate-limit find_places? +

Yes. Add a rate_limit block to the find_places 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_places completely? +

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

find_places is provided by the Seoul Essentials MCP server (do-droid/seoul-essentials). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Seoul Essentials tool call.

Deterministic rules across all 4 Seoul Essentials tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.