[Agent-Driven] Return ranked embedding recommendations based on hardware profile. Gets best-fit local/cloud models from MTEB-informed lookup table.
AI agents call search_embedding_recommendations to retrieve information from Strata Memory MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a lookup table to retrieve and rank embedding model recommendations. It performs a read-only retrieval operation that returns information to inform decision-making, with no side effects, data modification, or external execution. No destructive, financial, or code-execution capability is evident.
From the tool's definition Tool 'search_embedding_recommendations' returns ranked recommendations based on a hardware profile and lookup table. Uses words 'Return' and 'Gets' indicating retrieval operations with no modification of data or external side effects.
Attacks that exploit this kind of access
[Agent-Driven] Return ranked embedding recommendations based on hardware profile. Gets best-fit local/cloud models from MTEB-informed lookup table. It is categorised as a Read tool in the Strata Memory MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Strata Memory MCP Server MCP server in PolicyLayer and add a rule for search_embedding_recommendations: 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 Strata Memory MCP Server. Nothing to install.
search_embedding_recommendations 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_embedding_recommendations 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_embedding_recommendations. 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_embedding_recommendations is provided by the Strata Memory MCP Server MCP server (sherryli-vc/strata-memory). 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 →