Create feedback for a trace or request. Writes a new feedback record linked by trace_id, returns the created feedback IDs and status, and takes effect immediately; use update_feedback when correcting an existing record.
AI agents use create_feedback to create or update resources in Portkey Admin — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Portkey Admin environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
value | number | Yes | Feedback value/rating. Common patterns: 1 for positive (thumbs up), 0 for negative (thumbs down), or use a scale like 1-5. |
weight | number | — | Optional weighting factor for the feedback. Use to give more importance to certain feedback. |
metadata | object | — | Optional custom metadata for categorization and analysis (e.g., feedback_source, category, user_segment). |
trace_id | string | Yes | The trace ID to associate the feedback with. This links feedback to a specific request/generation. |
Parameters from the server's own tool schema.
An AI agent can call create_feedback faster than any human can review — one bad instruction and it creates or modifies resources in Portkey Admin by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Create feedback for a trace or request. Writes a new feedback record linked by trace_id, returns the created feedback IDs and status, and takes effect immediately; use update_feedback when correcting an existing record. It is categorised as a Write tool in the Portkey Admin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
create_feedback accepts 4 parameters: value, weight, metadata, trace_id. Required: value, trace_id. The full parameter table on this page comes from the server's own tool schema.
Register the Portkey Admin MCP server in PolicyLayer and add a rule for create_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 Portkey Admin. Nothing to install.
create_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 create_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 create_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.
create_feedback is provided by the Portkey Admin MCP server (CodesWhat/portkey-admin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.