Have a free-form conversation with Ember. Ask for advice, discuss approaches, or just chat. Ember responds with personality and contextual awareness.
AI agents call ember_chat 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.
This is a query/retrieval tool that obtains conversational responses. No side effects are described or implied. Even in the context of an agent-runtime system, the tool itself performs no writes, executions, or destructive operations — it only retrieves conversational advice. Confidence is high because the description is explicit about the read-only nature of the interaction.
From the tool's definition Tool description states 'Have a free-form conversation with Ember. Ask for advice, discuss approaches, or just chat.
Attacks that exploit this kind of access
Have a free-form conversation with Ember. Ask for advice, discuss approaches, or just chat. Ember responds with personality and contextual awareness. 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_chat: 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_chat 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_chat 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_chat. 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_chat 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 →