Search for documents without generating an answer
AI agents call search_documents to retrieve information from Chalee MCP RAG without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries stored documents to find matches based on search criteria. It retrieves information without side effects, altering data, or triggering external operations. This is a classic Read operation. The low severity reflects minimal risk even if misused by an AI agent—it can only expose information already in the knowledge base, not modify or delete it.
From the tool's definition Tool name 'search_documents' and description 'Search for documents without generating an answer' indicate a retrieval operation with no modification, deletion, or code execution.
Attacks that exploit this kind of access
Search for documents without generating an answer. It is categorised as a Read tool in the Chalee MCP RAG MCP Server, which means it retrieves data without modifying state.
Register the Chalee MCP RAG 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 Chalee MCP RAG. 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 Chalee MCP RAG MCP server (prettyking/chalee-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 →