Search for tours and experiences on GetExperience.com. Returns list of matching experiences with id, title, price, location, duration, rating, payment type, photos, booking link. BOOKING FLOW: search_experiences → get_experience_details → get_experience_schedule → add_to_checkout → create_order E...
Risk signalsHigh parameter count (24 properties) · Bulk/mass operation — affects multiple targets
Part of the GetExperience server.
Free to start. No card required.
AI agents call search_experiences to retrieve information from GetExperience 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 search_experiences 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.
{
"version": "1",
"default": "deny",
"tools": {
"search_experiences": {}
}
}See the full GetExperience policy for all 6 tools.
These attack patterns abuse exactly the kind of access search_experiences gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Search for tours and experiences on GetExperience.com. Returns list of matching experiences with id, title, price, location, duration, rating, payment type, photos, booking link. BOOKING FLOW: search_experiences → get_experience_details → get_experience_schedule → add_to_checkout → create_order EXAMPLES: - "walking tour in Istanbul" → location: "Istanbul", categories: ["walking-tour"] - "romantic dinner in Paris" → location: "Paris", categories: ["romantic", "food-and-drink"] - "things to do in Bali" → location: "Bali" - "водные виды спорта в Анталье" → location: "Antalya", categories: ["water-sports"] - "short private tour with free cancellation" → privateGroup: true, standardCancellation: true, durations: ["10-60"] - "tours with partial payment in Turkey" → countryCode: "TR", paymentOptions: "part" - "yacht party" → q: "yacht party" - "tours for solo traveler" → peopleMin: 1 - "tours with transport included" → features: ["transport"] All prices are in USD. SEARCH TIPS: - location: use English name for best results (e.g. "Istanbul" not "Стамбул"). Non-Latin input is supported but English is more reliable. - If location is not found, you'll get a clear error — not random results. Try a broader location (country instead of city). - "languages" filters tours by guide language (["es"] = tours in Spanish) - "lang" sets the language of titles and descriptions in the response - All filters can be combined: location + categories + paymentOptions + durations + standardCancellation etc. - "q" is a free-text search across titles and descriptions — use it for specific queries that don't fit into categories. ━━━ PAGINATION ━━━ Results are paginated (default 25 per page). The response always shows the total count and which results you're viewing (e.g. "showing 1–25 of 80"). If there are more results, ALWAYS offer the user to see the next page. Use page parameter to fetch subsequent pages. ━━━ HOW TO DISPLAY RESULTS AS CARDS ━━━ Every response includes a [GXP_STRUCTURED] block with structured JSON — use it to render rich experience cards in your UI instead of parsing markdown text. Parse it with: const match = text.match(/\[GXP_STRUCTURED\]([\s\S]*?)\[\/GXP_STRUCTURED\]/); const data = match ? JSON.parse(match[1].trim()) : null; // → data.items[] — each item has: id, title, price, priceCents, location, // durationMinutes, rating, reviewsCount, mainPhoto, photos[], paymentOptions, link To get pure JSON without markdown: set responseFormat: "json". It is categorised as a Read tool in the GetExperience MCP Server, which means it retrieves data without modifying state.
Register the GetExperience MCP server in PolicyLayer and add a rule for search_experiences: 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 GetExperience. Nothing to install.
search_experiences is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_experiences 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.
Set action: deny in the PolicyLayer policy for search_experiences. 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.
search_experiences is provided by the GetExperience MCP server (https://getexperience.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 GetExperience 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.