Events

18 tools. 6 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated:

6 can modify or destroy data
12 read-only
18 tools total

Community server · catalogue entry checked 07/07/2026 · full schemas captured for 17 of 18 tools

How to control Events ↓

What Events exposes to your agents

Read (12) Write / Execute (4) Destructive / Financial (2)

What Events costs in tokens

3,359 tokens of tool definitions, loaded on every request
1.7% of a 200k context window
379 heaviest tool: get_event_search_followups
Critical Risk

The most dangerous Events tools

6 of Events's 18 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Events

PolicyLayer is an MCP gateway — it sits between your AI agents and Events, and nothing reaches the server without passing your rules. These are the rules we recommend:

Block financial tools by default
{
  "purchase_ticket_order": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Deny destructive operations
{
  "delete_event_preferences": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "create_event_calendar_file": {
    "limits": [
      {
        "counter": "create_event_calendar_file_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "get_event": {
    "limits": [
      {
        "counter": "get_event_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Events — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON EVENTS →

Instant setup, no code required.

All 18 Events tools

READ 12 tools
Read get_event Use this when a user asks for details about a specific UPlayground event id returned by search, recommendation Read get_event_feedback_prompt Use this when a user previously picked or attended a UPlayground event and the assistant should ask a short po Read get_event_preferences Use this when a user with a UPlayground profile wants to view saved event preferences or learned recommendatio Read get_event_search_followups Use this when a user asks for events tonight, this week, or this weekend and the assistant should ask only the Read get_preference_onboarding Use this when a user wants personalized event recommendations and UPlayground needs consent-first questions be Read get_ticket_offers Use this when a user wants ticket options for a specific UPlayground event before quoting or buying. Read get_ticket_purchase_policy Use this when a user asks whether agents can buy tickets autonomously or what purchase modes UPlayground, Herm Read plan_night Use this when a user wants a compact night-out plan with a primary live event option and fallback options from Read quote_ticket_order Use this when a user has chosen an event and wants a locked ticket quote with quantity, max price, ticket type Read recommend_events Use this when a user wants ranked event suggestions from live UPlayground inventory based on the current reque Read recommend_events_for_user Use this when a user has a UPlayground preference profile and wants personalized event recommendations for ton Read search_events Use this when a user wants current events from live UPlayground inventory using filters such as city, date, ge

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Events

Can an AI agent move money through the Events MCP server? +

Yes. The Events server exposes 1 financial tools including purchase_ticket_order. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

Can an AI agent delete data through the Events MCP server? +

Yes. The Events server exposes 1 destructive tools including delete_event_preferences. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Events? +

The Events server has 4 write tools including create_event_calendar_file, create_event_preference_profile, record_event_feedback. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Events.

How many tools does the Events MCP server expose? +

18 tools across 4 categories: Destructive, Execute, Read, Write. 12 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Events? +

Register the Events MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Events tool call.

Deterministic rules across all 18 Events tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

18 Events tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Events's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.