Search memories and optionally include user profile information This tool searches for relevant memories and can also return the user's profile to provide context about the user for personalized responses. Args: query: Search query text user_id: User identifier (required) agent_id: Agent identifi...
AI agents call search_memories_with_profile to retrieve information from Mcp Oceanbase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation because it retrieves data (memories and optionally user profile information) without creating, modifying, or deleting anything. However, it reaches medium severity rather than low due to the potential for sensitive personal information exposure - user profiles and memory contexts could include private data that an AI agent might mishandle or leak.
From the tool's definition The tool "searches for relevant memories" and "can also return the user's profile" - these are retrieval operations with no modification capability. The description explicitly focuses on querying and fetching data.
Documented attack patterns abuse exactly the kind of access search_memories_with_profile gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Oceanbase, and nothing reaches the server without passing your rules. This is the rule we recommend for search_memories_with_profile:
{
"version": "1",
"default": "deny",
"tools": {
"search_memories_with_profile": {}
}
}search_memories_with_profile 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.
Search memories and optionally include user profile information This tool searches for relevant memories and can also return the user's profile to provide context about the user for personalized responses. Args: query: Search query text user_id: User identifier (required) agent_id: Agent identifier run_id: Run/session identifier limit: Maximum number of results (default 10) threshold: Similarity threshold (0.0-1.0) filters: Metadata filters add_profile: Whether to include user profile in results (default True) Returns: JSON formatted string containing: - Search results (memories) - profile_content: User's profile text (if add_profile=True and exists) - topics: User's structured topics (if add_profile=True and exists). It is categorised as a Read tool in the Mcp Oceanbase MCP Server, which means it retrieves data without modifying state.
Register the Mcp Oceanbase MCP server in PolicyLayer and add a rule for search_memories_with_profile: 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 Oceanbase. Nothing to install.
search_memories_with_profile 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_with_profile 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_with_profile. 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_with_profile is provided by the Mcp Oceanbase MCP server (oceanbase/awesome-oceanbase-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 134 Mcp Oceanbase tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
134 Mcp Oceanbase tools catalogued and risk-classified — across an index of 42,500+ MCP servers.