AI agents use record_event_feedback to create or update resources in Events — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Events environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
liked | boolean | — | |
notes | string | — | |
rating | number | — | |
event_id | string | Yes | |
profile_id | string | Yes | |
attended_at | string | — | ISO date/time or YYYY-MM-DD. |
profile_secret | string | Yes | Private profile secret returned when the profile was created. |
Parameters from the server's own tool schema.
This tool writes user feedback (ratings, likes/dislikes, notes) to a persistent store to influence future recommendations. It creates/modifies data reversibly with no financial, destructive, or execution implications. Severity is low because the blast radius of misuse is minimal — at worst, incorrect feedback skews personalized recommendations.
From the tool's definition 'record_event_feedback' — 'user says whether they liked or disliked a specific event, provides a rating, or shares notes, so future recommendations can learn from that feedback'
Attacks that exploit this kind of access
Use this when a user says whether they liked or disliked a specific event, provides a rating, or shares notes, so future UPlayground recommendations can learn from that feedback. It is categorised as a Write tool in the Events MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
record_event_feedback accepts 7 parameters: liked, notes, rating, event_id, profile_id, attended_at, profile_secret. Required: event_id, profile_id, profile_secret. 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 record_event_feedback: 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.
record_event_feedback is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the record_event_feedback 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 record_event_feedback. 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.
record_event_feedback 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.
record_event_feedback 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 →