search_memories
AI agents call search_memories to retrieve information from Mem0 Mcp Toggle without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool searches an existing local memory store without modifying, deleting, or executing external operations. Even though the description is empty, the name and sibling tools (add_memory, delete_memory, etc.) establish that this server manages memories, and 'search' is unambiguously a read operation.
From the tool's definition Tool name 'search_memories' indicates a query/retrieval operation. Server stores memories locally in Chroma (a vector database), and search is a standard read-only operation on such stores.
Attacks that exploit this kind of access
search_memories. It is categorised as a Read tool in the Mem0 Mcp Toggle MCP Server, which means it retrieves data without modifying state.
Register the Mem0 Mcp Toggle MCP server in PolicyLayer and add a rule for search_memories: 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 Mem0 Mcp Toggle. Nothing to install.
search_memories 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 search_memories 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 search_memories. 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.
search_memories is provided by the Mem0 Mcp Toggle MCP server (ost527/mem0-mcp-toggle). 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 →