leave_feedback
Ultra path: agent_name + rating (1–5) + body (one sentence). Demo optional. First 100 real feedbacks unlock full product free. Dense survey answers optional.
This record as markdown: /tools/dev-dualregistry-registry/leave-feedback.md
What leave_feedback does on Dual Registry
AI agents call leave_feedback to retrieve information from Dual Registry without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
sku | string | — | |
body | string | — | One sentence — what worked / blocked you |
mode | string | — | ultra | minimal | full |
rating | number | — | 1–5 overall |
answers | object | — | |
contact | string | — | |
audience | string | — | |
order_id | string | — | |
agent_name | string | Yes | |
listing_id | string | — |
Parameters from the server's own tool schema.
Why leave_feedback is rated Low
Even though leave_feedback only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsAccepts raw HTML/template content (body) · High parameter count (10 properties)
Attacks that exploit this kind of access
The rule that runs leave_feedback safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Dual Registry, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For leave_feedback, this is the rule to start with:
leave_feedback is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Dual Registry, apply this rule, and every leave_feedback call is checked against it from then on.
Questions about leave_feedback
Ultra path: agent_name + rating (1–5) + body (one sentence). Demo optional. First 100 real feedbacks unlock full product free. Dense survey answers optional. It is categorised as a Read tool in the Dual Registry MCP Server, which means it retrieves data without modifying state.
leave_feedback accepts 10 parameters: sku, body, mode, rating, answers, contact, audience, order_id, agent_name, listing_id. Required: agent_name. The full parameter table on this page comes from the server's own tool schema.
Register the Dual Registry MCP server in PolicyLayer and add a rule for leave_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 Dual Registry. Nothing to install.
leave_feedback 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 leave_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 leave_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.
leave_feedback is provided by the Dual Registry MCP server (https://www.dualregistry.dev/api/protocol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Dual Registry, and thousands of servers like it.
This server
Across the catalogue