memory.recall · Lore Context MCP: Risk & Policy

WHAT IT DOES

What memory.recall does on Lore Context

AI agents call memory.recall to retrieve information from Lore Context 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 memory.recall needs a policy

The tool recalls and retrieves previously stored context and trace information. The mention of 'governed' and 'audit' suggests read-only access to memory state. No indication of writing, executing, destructing, or financial operations. Returns a trace ID for audit purposes, confirming it is a query/retrieval function with no side effects.

From the tool's definition Tool description states it 'Composes governed, agent-ready context and returns its trace id for audit' — a retrieval operation that returns existing context and trace information with no modification or deletion of underlying data.

Attacks that exploit this kind of access

Questions about memory.recall

What does the memory.recall tool do? +

Hosted MCP recall entrypoint. Composes governed, agent-ready context and returns its trace id for audit. It is categorised as a Read tool in the Lore Context MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on memory.recall? +

Register the Lore Context MCP server in PolicyLayer and add a rule for memory.recall: 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 Lore Context. Nothing to install.

What risk level is memory.recall? +

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

Can I rate-limit memory.recall? +

Yes. Add a rate_limit block to the memory.recall 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 memory.recall completely? +

Set action: deny in the PolicyLayer policy for memory.recall. 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 memory.recall? +

memory.recall is provided by the Lore Context MCP server (Lore-Context/lore-context). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.