Search memories by text query within a namespace. Uses full-text search.
AI agents call memory_search to retrieve information from Mcp Services without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only full-text search query against stored memories. It retrieves data without side effects, making it a classic Read category tool. The low severity reflects minimal risk—querying existing data poses no blast radius for unintended modifications or external operations.
From the tool's definition Tool name 'memory_search' and description 'Search memories by text query within a namespace. Uses full-text search' indicate a retrieval operation with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Search memories by text query within a namespace. Uses full-text search. It is categorised as a Read tool in the Mcp Services MCP Server, which means it retrieves data without modifying state.
Register the Mcp Services 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 Mcp Services. 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 Mcp Services MCP server (san-npm/mcp-services). 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 →