Search chat history for a keyword, returning full conversation turns.
AI agents call memory_search to retrieve information from OpenClaw Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries stored conversation data and returns results without creating, modifying, or deleting any records. It is a straightforward search/retrieval operation with no capability to alter state or trigger external actions. The blast radius of misuse is minimal — an agent might retrieve unintended conversation history, but cannot cause data loss or execute operations.
From the tool's definition Tool name 'memory_search' and description states it 'Search chat history for a keyword, returning full conversation turns' — pure information retrieval with no modifications or side effects.
Attacks that exploit this kind of access
Search chat history for a keyword, returning full conversation turns. It is categorised as a Read tool in the OpenClaw Memory MCP Server, which means it retrieves data without modifying state.
Register the OpenClaw Memory MCP server in PolicyLayer and add a rule for memory_search: 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 OpenClaw Memory. Nothing to install.
memory_search 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_search 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_search. 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_search is provided by the OpenClaw Memory MCP server (liuhao6741/openclaw-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 →