Search and filter memories. Supports lexical (keyword), semantic (vector similarity), and hybrid (RRF fusion of both) search modes. Filters by namespace prefix, entry type, tags, time range (since/until), and optional expiry handling. Can be used without a query to browse by filters alone (e.g. a...
AI agents call memory_query to retrieve information from Munin Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a querying tool that retrieves and searches stored memory data without side effects. While the data being accessed could be sensitive personal or contextual information (raising severity above 'low'), the tool itself performs only Read operations.
From the tool's definition Tool performs 'Search and filter memories' with support for 'lexical (keyword), semantic (vector similarity), and hybrid (RRF fusion of both) search modes' and 'Filters by namespace prefix, entry type, tags, time range'.
Attacks that exploit this kind of access
Search and filter memories. Supports lexical (keyword), semantic (vector similarity), and hybrid (RRF fusion of both) search modes. Filters by namespace prefix, entry type, tags, time range (since/until), and optional expiry handling. Can be used without a query to browse by filters alone (e.g. all entries with a specific tag, or all entries updated today). Broad retrieval hides expired state entries by default; use. It is categorised as a Read tool in the Munin Memory MCP Server, which means it retrieves data without modifying state.
Register the Munin Memory MCP server in PolicyLayer and add a rule for memory_query: 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 Munin Memory. Nothing to install.
memory_query 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_query 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_query. 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_query is provided by the Munin Memory MCP server (magnus-gille/munin-memory). 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 →