kdbai_similarity_search
AI agents call kdbai_similarity_search to retrieve information from KDB AI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Similarity search in vector databases is a quintessential Read operation—it queries and retrieves data based on vector similarity without creating, modifying, or deleting records. No side effects are expected from executing a search query.
From the tool's definition Tool name 'kdbai_similarity_search' indicates a search operation typical of vector database queries. The server description emphasizes 'similarity searches' as a core capability for 'retrieval' operations.
Attacks that exploit this kind of access
kdbai_similarity_search. It is categorised as a Read tool in the KDB AI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the KDB AI MCP Server MCP server in PolicyLayer and add a rule for kdbai_similarity_search: 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 KDB AI MCP Server. Nothing to install.
kdbai_similarity_search 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 kdbai_similarity_search 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 kdbai_similarity_search. 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.
kdbai_similarity_search is provided by the KDB AI MCP Server MCP server (kxsystems/kdbai-mcp-server). 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 →