perform_rag_query

What perform_rag_query does on Obsidian Elite RAG MCP Server

AI agents call perform_rag_query to retrieve information from Obsidian Elite RAG MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why perform_rag_query is rated Low

RAG query operations are fundamentally read-only—they retrieve and search existing knowledge without modifying, deleting, or executing external operations. The sibling tools include memory and observation management (write-like), project analysis (read), and data manipulation (read/write), but 'perform_rag_query' itself appears designed solely for information retrieval from the vault.

From the tool's definition Tool name 'perform_rag_query' indicates a query operation against a RAG (Retrieval-Augmented Generation) system. The server description emphasizes 'semantic search' and 'knowledge graph integration' for retrieving information from Obsidian vaults.

The rule that runs perform_rag_query safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Obsidian Elite RAG MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For perform_rag_query, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "perform_rag_query": {}
  }
}

Questions about perform_rag_query