Low Risk

search_memories

Search memories Args: query: Search query text user_id: User identifier 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 Returns: JSON formatted string

How to control search_memories ↓

AI agents call search_memories 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.

Low Risk

This tool retrieves or queries memory data based on provided search criteria and filters. It has no side effects—it does not create, modify, delete, execute code, or move money. The similarity threshold and limit parameters are standard for read-only search operations. Classification as Read is appropriate.

From the tool's definition Tool name 'search_memories' and description 'Search memories' indicate a query/retrieval operation. Parameters include search query, user_id, agent_id, run_id, limit, threshold, and filters—all typical of search/filtering operations.

Documented attack patterns abuse exactly the kind of access search_memories 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:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_memories": {}
  }
}

search_memories is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Mcp Oceanbase — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the search_memories tool do? +

Search memories Args: query: Search query text user_id: User identifier 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 Returns: JSON formatted string. It is categorised as a Read tool in the Mcp Oceanbase MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_memories? +

Register the Mcp Oceanbase 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 Mcp Oceanbase. Nothing to install.

What risk level is search_memories? +

search_memories is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit search_memories? +

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.

How do I block search_memories completely? +

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.

What MCP server provides search_memories? +

search_memories 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.

Enforce policy on every Mcp Oceanbase tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.