Low Risk

search_deals

Search grocery deals across stores by keyword. Supports Denmark (DK), Norway (NO), Sweden (SE), and Finland (FI) based on household country setting. USE WHEN: finding specific products, checking prices, comparing stores. NOT FOR: browsing one store

How to control search_deals ↓

What search_deals does on TilbudsTrolden

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

Low Risk

Why search_deals needs a policy

search_deals retrieves grocery deal information based on keyword input and returns price/availability data across stores. This is a pure query operation with no capability to modify data, execute commands, or cause irreversible changes. The low severity reflects minimal blast radius if misused by an AI agent — worst case would be retrieving irrelevant deal information or spam searches.

From the tool's definition Tool performs "search" and "finding specific products, checking prices, comparing stores" — core read operations that query and retrieve data without modification or side effects.

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

How to control search_deals

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

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

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

  1. Create a free account and register TilbudsTrolden — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about search_deals

What does the search_deals tool do? +

Search grocery deals across stores by keyword. Supports Denmark (DK), Norway (NO), Sweden (SE), and Finland (FI) based on household country setting. USE WHEN: finding specific products, checking prices, comparing stores. NOT FOR: browsing one store. It is categorised as a Read tool in the TilbudsTrolden MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_deals? +

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

What risk level is search_deals? +

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

Can I rate-limit search_deals? +

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

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

search_deals is provided by the TilbudsTrolden MCP server (olgasafonova/tilbudstrolden-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every TilbudsTrolden tool call.

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

Free to start. No card required.

18 TilbudsTrolden tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.