AI agents call recommend_events to retrieve information from Events without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
city | string | — | City name, for example berlin or new york. |
free | boolean | — | |
vibe | array | — | |
when | string | — | Date preset: today, tonight, tomorrow, weekend, week, this week, any, or YYYY-MM-DD. |
avoid | array | — | Terms to penalize in recommendations. |
limit | number | — | Results per page (default 12). The response's count field is the TOTAL matching events — raise limit or use offset to page through more. |
pride | boolean | — | |
query | string | — | Keyword search. |
venue | string | — | |
genres | array | — | |
offset | number | — | |
date_to | string | — | Inclusive end date in YYYY-MM-DD format. |
Parameters from the server's own tool schema.
The tool queries and retrieves event recommendations from inventory based on filtering parameters (taste, vibe, price, avoid signals). This is a read-only operation with no side effects. It returns data to inform user decisions but does not create, modify, delete, or execute any actions. The blast radius of misuse is minimal—worst case, a user receives irrelevant or unwanted event suggestions, which is non-damaging.
From the tool's definition Tool provides 'ranked event suggestions' and 'retrieve' operation based on user preferences and signals. No modification, deletion, or execution of external operations occurs.
Risk signalsHigh parameter count (20 properties)
Attacks that exploit this kind of access
Use this when a user wants ranked event suggestions from live UPlayground inventory based on the current request's taste, vibe, price, and avoid signals. It is categorised as a Read tool in the Events MCP Server, which means it retrieves data without modifying state.
recommend_events accepts 12 parameters: city, free, vibe, when, avoid, limit, pride, query, venue, genres, offset, date_to. The full parameter table on this page comes from the server's own tool schema.
Register the Events MCP server in PolicyLayer and add a rule for recommend_events: 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 Events. Nothing to install.
recommend_events 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 recommend_events 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 recommend_events. 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.
recommend_events is provided by the Events MCP server (uplayground-events). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
recommend_events is one line of Events's registry record.
The record carries the whole server: 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 →