update_feedback · Portkey Admin MCP: Risk & Policy

WHAT IT DOES

What update_feedback does on Portkey Admin

AI agents use update_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.

PARAMETERS

Parameter	Type	Required	Description
`id`	string	Yes	The unique identifier of the feedback to update
`value`	number	—	New feedback value/rating. Common patterns: 1 for positive, 0 for negative.
`weight`	number	—	New weighting factor for the feedback
`metadata`	object	—	New or updated custom metadata for the feedback

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why update_feedback needs a policy

An AI agent can call update_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

Recommended rule Ready

Verdict

update_feedback Rate-limited

update_feedback stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_feedback": {
      "limits": [
        {
          "counter": "update_feedback_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Portkey Admin, so you can run agents against it safely.

FAQ

Questions about update_feedback

What does the update_feedback tool do? +

Update an existing feedback record by ID. Returns the updated status and feedback IDs, changes only value, weight, and metadata, and leaves the trace linkage immutable; use create_feedback only for a new 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.

What parameters does update_feedback accept? +

update_feedback accepts 4 parameters: id, value, weight, metadata. Required: id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on update_feedback? +

Register the Portkey Admin MCP server in PolicyLayer and add a rule for update_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.

What risk level is update_feedback? +

update_feedback is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit update_feedback? +

Yes. Add a rate_limit block to the update_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.

How do I block update_feedback completely? +

Set action: deny in the PolicyLayer policy for update_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.

What MCP server provides update_feedback? +

update_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.