Search for relevant document chunks using semantic similarity
AI agents call search to retrieve information from MCP RAG Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The search tool performs a query operation that retrieves information from the vector database without creating, modifying, deleting, or executing anything. It is a straightforward read operation typical of RAG systems. The low severity reflects that retrieving document chunks poses minimal risk even if misused by an AI agent, as the operation is idempotent and has no side effects.
From the tool's definition Tool description states 'Search for relevant document chunks using semantic similarity' - a retrieval operation with no modification or execution capability. The server is explicitly a RAG system for ingesting and searching documents.
Attacks that exploit this kind of access
Search for relevant document chunks using semantic similarity. It is categorised as a Read tool in the MCP RAG Server MCP Server, which means it retrieves data without modifying state.
Register the MCP RAG Server MCP server in PolicyLayer and add a rule for 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 MCP RAG Server. Nothing to install.
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 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 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.
search is provided by the MCP RAG Server MCP server (luizdopc/mcp-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 →