Talk to Sage — your personalized AI cooking companion. Sage knows your family
AI agents call sage_chat to retrieve information from Old Family Recipe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a chat/conversational tool that queries an AI assistant. The description is truncated but implies it reads family recipe context to provide personalized cooking advice. No write, execute, or destructive actions are indicated. Confidence is moderate due to the incomplete description — a chat tool could theoretically trigger other actions, but the primary function appears to be read/query.
From the tool's definition 'Talk to Sage — your personalized AI cooking companion. Sage knows your family' — conversational/chat interface that retrieves personalized responses
Attacks that exploit this kind of access
Talk to Sage — your personalized AI cooking companion. Sage knows your family. It is categorised as a Read tool in the Old Family Recipe MCP Server, which means it retrieves data without modifying state.
Register the Old Family Recipe MCP server in PolicyLayer and add a rule for sage_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 Old Family Recipe. Nothing to install.
sage_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 sage_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 sage_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.
sage_chat is provided by the Old Family Recipe MCP server (oldfamilyrecipe/ai). 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 →