Search memories by semantic similarity to a natural language query. Uses multi-signal scoring: vector similarity, temporal decay, recency, importance, and optional knowledge graph expansion. Args: query: Natural language search query. top_k: Maximum number of results (default 10). memory_type: Fi...
AI agents call memory_recall to retrieve information from Yantrikdb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
memory_recall is a query/search tool that retrieves stored memories based on semantic similarity and filtering criteria. It has no side effects on the data store—it only returns results. The tool fits the 'Read' category as it retrieves or queries data without creating, modifying, or deleting anything.
From the tool's definition Tool performs 'Search memories by semantic similarity' with parameters for querying existing data (query, top_k, memory_type filters, namespace). No modifications, deletions, or external operations are performed.
Documented attack patterns abuse exactly the kind of access memory_recall gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Yantrikdb, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_recall:
{
"version": "1",
"default": "deny",
"tools": {
"memory_recall": {}
}
}memory_recall 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 by semantic similarity to a natural language query. Uses multi-signal scoring: vector similarity, temporal decay, recency, importance, and optional knowledge graph expansion. Args: query: Natural language search query. top_k: Maximum number of results (default 10). memory_type: Filter by type ('episodic', 'semantic', 'procedural'). None for all. include_consolidated: Whether to include consolidated (merged) memories. expand_entities: Whether to use knowledge graph to find related memories. namespace: Filter by namespace. None returns all namespaces. domain: Filter by topic domain (work, health, family, etc.). None for all. source: Filter by memory source (user, system, document, inference). None for all. Returns matching memories ranked by relevance with score breakdowns. It is categorised as a Read tool in the Yantrikdb MCP Server, which means it retrieves data without modifying state.
Register the Yantrikdb MCP server in PolicyLayer and add a rule for memory_recall: 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 Yantrikdb. Nothing to install.
memory_recall 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_recall 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_recall. 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_recall is provided by the Yantrikdb MCP server (yantrikos/yantrikdb-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 Yantrikdb tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 Yantrikdb tools catalogued and risk-classified — across an index of 42,500+ MCP servers.