AI agents call search_documentation to retrieve information from MCP-Ragdocs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic search queries against a vector database to retrieve documentation. It retrieves and queries data without side effects, matching the Read category definition. The severity is low because search operations cannot harm system integrity or data—they only access existing information. Confidence is high due to the clear semantic evidence in both the tool name and description.
From the tool's definition Tool name 'search_documentation' and description 'Search through stored documentation' indicate retrieval of existing data with no modification or deletion capabilities.
Documented attack patterns abuse exactly the kind of access search_documentation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Ragdocs, and nothing reaches the server without passing your rules. This is the rule we recommend for search_documentation:
{
"version": "1",
"default": "deny",
"tools": {
"search_documentation": {}
}
}search_documentation 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 through stored documentation. It is categorised as a Read tool in the MCP-Ragdocs MCP Server, which means it retrieves data without modifying state.
Register the MCP-Ragdocs MCP server in PolicyLayer and add a rule for search_documentation: 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-Ragdocs. Nothing to install.
search_documentation 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_documentation 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_documentation. 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_documentation is provided by the MCP-Ragdocs MCP server (qpd-v/mcp-ragdocs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 MCP-Ragdocs tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 MCP-Ragdocs tools catalogued and risk-classified — across an index of 42,500+ MCP servers.