Search based on semantic similarity
AI agents call search_semantic_similarity to retrieve information from RAG-MCP Knowledge Base Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic search—a read-only operation that queries and retrieves data without side effects. It searches vector embeddings to find similar documents but does not create, modify, delete, or execute code. The operation is purely informational retrieval, fitting the Read category with low severity.
From the tool's definition Tool name 'search_semantic_similarity' and description 'Search based on semantic similarity' indicate a retrieval/query operation across vector embeddings in PostgreSQL. No creation, modification, deletion, execution, or financial operations are described.
Attacks that exploit this kind of access
Search based on semantic similarity. It is categorised as a Read tool in the RAG-MCP Knowledge Base Server MCP Server, which means it retrieves data without modifying state.
Register the RAG-MCP Knowledge Base Server MCP server in PolicyLayer and add a rule for search_semantic_similarity: 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 RAG-MCP Knowledge Base Server. Nothing to install.
search_semantic_similarity 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_semantic_similarity 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_semantic_similarity. 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_semantic_similarity is provided by the RAG-MCP Knowledge Base Server MCP server (luxter77/mcp-kbdb). 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 →