ember_get_feedback · Agent Runtime MCP: Risk & Policy

WHAT IT DOES

What ember_get_feedback does on Agent Runtime

AI agents call ember_get_feedback to retrieve information from Agent Runtime without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

WHY IT NEEDS A POLICY

Why ember_get_feedback needs a policy

The 'get' verb and lack of destructive/modifying language classify this as a Read operation. The minimal description reduces confidence slightly, but the clear retrieval semantics and the context of a task/goal management system (where 'get feedback' would typically retrieve status or results) support Read classification. Severity is low as it only queries data with no blast radius.

From the tool's definition Tool name 'ember_get_feedback' uses verb 'get', which indicates data retrieval with no side effects. Description 'Get Ember' is minimal and uninformative but suggests a query or fetch operation.

Attacks that exploit this kind of access

Questions about ember_get_feedback

What does the ember_get_feedback tool do? +

Get Ember. It is categorised as a Read tool in the Agent Runtime MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on ember_get_feedback? +

Register the Agent Runtime MCP server in PolicyLayer and add a rule for ember_get_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 Agent Runtime. Nothing to install.

What risk level is ember_get_feedback? +

ember_get_feedback is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit ember_get_feedback? +

Yes. Add a rate_limit block to the ember_get_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 ember_get_feedback completely? +

Set action: deny in the PolicyLayer policy for ember_get_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 ember_get_feedback? +

ember_get_feedback is provided by the Agent Runtime MCP server (marc-shade/agent-runtime-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.