Low Risk

find_product

Smart router — finds the best place to stream, buy, or collect any supported product. Automatically detects the product category and routes to the right resolver. Music is live (stream, digital purchase, vinyl, CD, collector editions). Games, books, films, podcasts, and live event tickets are rol...

Risk signalsAccepts freeform code/query input (query)

Part of the Rootvine server.

find_product 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 ROOTVINE →

Free to start. No card required.

AI agents call find_product to retrieve information from Rootvine 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_product 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_product": {}
  }
}

See the full Rootvine policy for all 4 tools.

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

ENFORCE ON MY ROOTVINE →

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

SECURE ROOTVINE →

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

What does the find_product tool do? +

Smart router — finds the best place to stream, buy, or collect any supported product. Automatically detects the product category and routes to the right resolver. Music is live (stream, digital purchase, vinyl, CD, collector editions). Games, books, films, podcasts, and live event tickets are rolling out. Use this when the query is ambiguous or when music could be streamed, purchased digitally, or found on physical media.. It is categorised as a Read tool in the Rootvine MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on find_product? +

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

What risk level is find_product? +

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

Can I rate-limit find_product? +

Yes. Add a rate_limit block to the find_product 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_product completely? +

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

find_product is provided by the Rootvine MCP server (rootvine-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Rootvine tool call.

Deterministic rules across all 4 Rootvine 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.