Unified memory retrieval — classifies your query and routes to the optimal search backend automatically. Use this instead of choosing between search/vsearch/query/intent_search. Auto-routing: -
AI agents call memory_retrieve to retrieve information from ClawMem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries stored memory data and automatically classifies/routes queries to the optimal search backend. No side effects, modifications, or deletions are described or implied. It is purely a retrieval mechanism for persistent context storage, fitting squarely in the 'Read' category.
From the tool's definition Tool name 'memory_retrieve' and description 'Unified memory retrieval' with routing to 'search backend' indicates data querying only.
Documented attack patterns abuse exactly the kind of access memory_retrieve gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ClawMem, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_retrieve:
{
"version": "1",
"default": "deny",
"tools": {
"memory_retrieve": {}
}
}memory_retrieve is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Unified memory retrieval — classifies your query and routes to the optimal search backend automatically. Use this instead of choosing between search/vsearch/query/intent_search. Auto-routing: -. It is categorised as a Read tool in the ClawMem MCP Server, which means it retrieves data without modifying state.
Register the ClawMem MCP server in PolicyLayer and add a rule for memory_retrieve: 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 ClawMem. Nothing to install.
memory_retrieve 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_retrieve 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_retrieve. 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_retrieve is provided by the ClawMem MCP server (yoloshii/clawmem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 30 ClawMem tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
30 ClawMem tools catalogued and risk-classified — across an index of 42,500+ MCP servers.