Search ingested documents with hybrid keyword + semantic matching. Returns results sorted by relevance, each with filePath, chunkIndex, text, fileTitle, score (0 = best, higher = worse), and source (for ingest_data items).
AI agents call query_documents to retrieve information from Mcp Local Rag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation across previously ingested documents using hybrid matching. It retrieves and returns ranked results but does not create, modify, delete, or execute any external operations. The only information exposed is document content already stored in the system, presenting minimal risk of misuse by an AI agent.
From the tool's definition Tool description explicitly states 'Search ingested documents' and 'Returns results sorted by relevance'. The verb 'query' combined with 'search' and result-return indicates data retrieval without modification.
Attacks that exploit this kind of access
Search ingested documents with hybrid keyword + semantic matching. Returns results sorted by relevance, each with filePath, chunkIndex, text, fileTitle, score (0 = best, higher = worse), and source (for ingest_data items). It is categorised as a Read tool in the Mcp Local Rag MCP Server, which means it retrieves data without modifying state.
Register the Mcp Local Rag MCP server in PolicyLayer and add a rule for query_documents: 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 Mcp Local Rag. Nothing to install.
query_documents 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 query_documents 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 query_documents. 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.
query_documents is provided by the Mcp Local Rag MCP server (mcp-local-rag). 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 →