Search for relevant document chunks using semantic similarity
AI agents call search_documents to retrieve information from MCP RAG System without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns data based on semantic search queries. It does not create, modify, delete, execute code, or move funds. The operation is read-only and returns results without altering the underlying document corpus or system state.
From the tool's definition Tool performs 'search for relevant document chunks using semantic similarity' - a retrieval operation with no data modification or side effects. It queries indexed vectors to return matching content.
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 System MCP Server, which means it retrieves data without modifying state.
Register the MCP RAG System 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 MCP RAG System. 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 MCP RAG System MCP server (nitin-kumar101/mcp). 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 →