AI agents call search_memories to retrieve information from Mentedb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | integer | null | — | Maximum number of results to return (default: 10) |
query | string | Yes | Search query text for semantic search, OR a memory UUID to get full content by ID |
memory_type | string | null | — | Optional memory type filter: episodic, semantic, procedural, anti_pattern, reasoning, correction |
Parameters from the server's own tool schema.
This tool performs read-only operations: searching and retrieving data from a memory store. It has no capability to create, modify, delete, or execute external operations. The blast radius of misuse is limited to information disclosure, which is low-severity for a persistent memory system.
From the tool's definition Tool description states: 'Search memories by semantic similarity, or get full content of a specific memory by UUID.
Risk signalsAccepts freeform code/query input (query)
Attacks that exploit this kind of access
Search memories by semantic similarity, or get full content of a specific memory by UUID. Use when you need to look up what you know about a topic, or to get the full text of a truncated context entry. It is categorised as a Read tool in the Mentedb MCP Server, which means it retrieves data without modifying state.
search_memories accepts 3 parameters: limit, query, memory_type. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Mentedb 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 Mentedb. 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 Mentedb MCP server (mentedb-mcp). 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 →