Low Risk

find_gifts

Search the curated Surprise Buddy database for gift ideas matching a recipient. Returns product cards with title, image, price, why-it-fits, and a clickable product URL. Country is required and is a hard filter — results are scoped to the marketplace + currency of that country.

Risk signalsHigh parameter count (10 properties)

Part of the Surprise Buddy server.

find_gifts 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 SURPRISE BUDDY →

Free to start. No card required.

AI agents call find_gifts to retrieve information from Surprise Buddy 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_gifts 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_gifts": {}
  }
}

See the full Surprise Buddy policy for all 5 tools.

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

ENFORCE ON MY SURPRISE BUDDY →

These attack patterns abuse exactly the kind of access find_gifts 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_gifts only ever does what you allow.

SECURE SURPRISE BUDDY →

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

What does the find_gifts tool do? +

Search the curated Surprise Buddy database for gift ideas matching a recipient. Returns product cards with title, image, price, why-it-fits, and a clickable product URL. Country is required and is a hard filter — results are scoped to the marketplace + currency of that country.. It is categorised as a Read tool in the Surprise Buddy MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on find_gifts? +

Register the Surprise Buddy MCP server in PolicyLayer and add a rule for find_gifts: 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 Surprise Buddy. Nothing to install.

What risk level is find_gifts? +

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

Can I rate-limit find_gifts? +

Yes. Add a rate_limit block to the find_gifts 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_gifts completely? +

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

find_gifts is provided by the Surprise Buddy MCP server (surprise-buddy/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Surprise Buddy tool call.

Deterministic rules across all 5 Surprise Buddy 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.