Search through indexed documents using semantic similarity. Returns the most relevant document chunks for a given query. This uses AI embeddings to find contextually similar content, not just keyword matches.
AI agents call search_documents to retrieve information from Multi-Agent RAG MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries indexed legal documents without side effects. It performs semantic search to return matching document chunks, consistent with the 'Read' category for search operations. The use of embeddings for similarity matching does not elevate it beyond information retrieval. No data creation, modification, deletion, code execution, or financial operations are described.
From the tool's definition Tool description states it 'Search through indexed documents' and 'Returns the most relevant document chunks' with no mention of modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Search through indexed documents using semantic similarity. Returns the most relevant document chunks for a given query. This uses AI embeddings to find contextually similar content, not just keyword matches. It is categorised as a Read tool in the Multi-Agent RAG MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Multi-Agent RAG MCP Server MCP server in PolicyLayer and add a rule for search_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 Multi-Agent RAG MCP Server. Nothing to install.
search_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 search_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 search_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.
search_documents is provided by the Multi-Agent RAG MCP Server MCP server (tsarri/rag-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 →