Search for semantically relevant documents based on query
AI agents call search_documents to retrieve information from MCP-Markdown-RAG without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs semantic search across indexed markdown documents and returns results. It retrieves data without modifying, deleting, or executing external operations. This is a classic Read operation with minimal blast radius even if misused by an AI agent, as the worst outcome is retrieving irrelevant or unintended documents.
From the tool's definition Tool name is 'search_documents' and description states 'Search for semantically relevant documents based on query' — this is a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access search_documents gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Markdown-RAG, and nothing reaches the server without passing your rules. This is the rule we recommend for search_documents:
{
"version": "1",
"default": "deny",
"tools": {
"search_documents": {}
}
}search_documents is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for semantically relevant documents based on query. It is categorised as a Read tool in the MCP-Markdown-RAG MCP Server, which means it retrieves data without modifying state.
Register the MCP-Markdown-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 MCP-Markdown-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 MCP-Markdown-RAG MCP server (zackriya-solutions/mcp-markdown-rag). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 MCP-Markdown-RAG tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
3 MCP-Markdown-RAG tools catalogued and risk-classified — across an index of 42,500+ MCP servers.