memory_lookup
AI agents call memory_lookup to retrieve information from 0CompactMem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'memory_lookup' strongly implies a read operation that retrieves or queries persistent memory state. Although the description is empty and reduces certainty, the naming convention aligns with diagnostic/informational tools rather than write, delete, or execution operations.
From the tool's definition Tool name 'memory_lookup' suggests a retrieval operation. The description is empty, which limits confidence, but the name pattern and context among sibling tools (list_pinned, memory_stats, memory_applied) indicates query/retrieval without modification.
Attacks that exploit this kind of access
memory_lookup. It is categorised as a Read tool in the 0CompactMem MCP Server, which means it retrieves data without modifying state.
Register the 0CompactMem MCP server in PolicyLayer and add a rule for memory_lookup: 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 0CompactMem. Nothing to install.
memory_lookup 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 memory_lookup 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 memory_lookup. 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.
memory_lookup is provided by the 0CompactMem MCP server (soolaugust/0compactmem). 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 →