Low Risk

polvenn_search_new_beers

Search for recently released beers on Vinmonopolet via the official API and/or your external release feed. Args: - source ('vinmonopolet' | 'external' | 'both'): Where to search (default: 'both') - since (string, optional): Best-effort date filter yyyy-MM-dd using external release dates, oth...

Part of the Polvenn MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

AI agents call polvenn_search_new_beers to retrieve information from Polvenn 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 polvenn_search_new_beers 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.

polvenn.yaml
tools:
  polvenn_search_new_beers:
    rules:
      - action: allow

See the full Polvenn policy for all 8 tools.

Tool Name polvenn_search_new_beers
Category Read
MCP Server Polvenn MCP Server
Risk Level Low

Agents calling read-class tools like polvenn_search_new_beers have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the polvenn_search_new_beers tool do? +

Search for recently released beers on Vinmonopolet via the official API and/or your external release feed. Args: - source ('vinmonopolet' | 'external' | 'both'): Where to search (default: 'both') - since (string, optional): Best-effort date filter yyyy-MM-dd using external release dates, otherwise Vinmonopolet lastChanged - includeUpcoming (boolean): Also include beers from Vinmonopolet's "Kommende nyheter" web filter - style (string, optional): Filter by beer style, e.g. 'IPA', 'Stout' - releaseDate (string, optional): Exact release date filter - storeId (string, optional): Limit Vinmonopolet-backed results to beers available in one store - limit (number): Max results (default: 25) Returns: List of new beers with name, producer, style, ABV, article number, and release date.. It is categorised as a Read tool in the Polvenn MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on polvenn_search_new_beers? +

Add a rule in your Intercept YAML policy under the tools section for polvenn_search_new_beers. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Polvenn MCP server.

What risk level is polvenn_search_new_beers? +

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

Can I rate-limit polvenn_search_new_beers? +

Yes. Add a rate_limit block to the polvenn_search_new_beers rule in your Intercept 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 polvenn_search_new_beers completely? +

Set action: deny in the Intercept policy for polvenn_search_new_beers. 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 polvenn_search_new_beers? +

polvenn_search_new_beers is provided by the Polvenn MCP server (@henrikogard/polvenn-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.