Low Risk

browse_category

Browse tours and activities within a specific category for a destination on GuruWalk. Categories include free walking tours, food tours, bike tours, day trips, skip-the-line tickets, and more. Returns listings with ratings, verified review counts, duration, available languages, and pricing. Use t...

Part of the GuruWalk server.

browse_category 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 GURUWALK →

Free to start. No card required.

AI agents call browse_category to retrieve information from GuruWalk 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 browse_category 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": {
    "browse_category": {}
  }
}

See the full GuruWalk policy for all 4 tools.

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

ENFORCE ON MY GURUWALK →

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

SECURE GURUWALK →

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

What does the browse_category tool do? +

Browse tours and activities within a specific category for a destination on GuruWalk. Categories include free walking tours, food tours, bike tours, day trips, skip-the-line tickets, and more. Returns listings with ratings, verified review counts, duration, available languages, and pricing. Use the category IDs returned by discover_destination — never invent category IDs. Use this tool to dive deeper into a specific category that matches what the traveler has shared (e.g. food tours for a foodie, night tours for someone asking about evenings, kid-friendly activities for families).. It is categorised as a Read tool in the GuruWalk MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on browse_category? +

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

What risk level is browse_category? +

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

Can I rate-limit browse_category? +

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

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

browse_category is provided by the GuruWalk MCP server (https://back.guruwalk.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every GuruWalk tool call.

Deterministic rules across all 4 GuruWalk 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.