Get statistics on Ember
AI agents call ember_get_learning_stats 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.
The verb 'Get' combined with 'statistics' clearly indicates a read-only query operation. There is no indication of side effects, data modification, code execution, or destructive actions. The low severity reflects that statistics retrieval has minimal blast radius even if misused by an AI agent.
From the tool's definition Tool name 'ember_get_learning_stats' and description 'Get statistics on Ember' indicate a retrieval operation that queries statistics without modifying or executing external actions.
Attacks that exploit this kind of access
Get statistics on Ember. It is categorised as a Read tool in the Agent Runtime MCP Server, which means it retrieves data without modifying state.
Register the Agent Runtime MCP server in PolicyLayer and add a rule for ember_get_learning_stats: 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.
ember_get_learning_stats 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 ember_get_learning_stats 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 ember_get_learning_stats. 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.
ember_get_learning_stats 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →