AI agents call search_knowledge_base to retrieve information from RAD Security without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves information from an organizational knowledge base. The 'search' verb and lack of any modification, execution, or deletion language confirm it performs read-only operations. The low severity reflects minimal blast radius—misuse would retrieve information but not alter systems or data.
From the tool's definition Tool name 'search_knowledge_base' combined with description 'Search your organization' indicates a query/retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access search_knowledge_base gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RAD Security, and nothing reaches the server without passing your rules. This is the rule we recommend for search_knowledge_base:
{
"version": "1",
"default": "deny",
"tools": {
"search_knowledge_base": {}
}
} search_knowledge_base 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 your organization. It is categorised as a Read tool in the RAD Security MCP Server, which means it retrieves data without modifying state.
Register the RAD Security MCP server in PolicyLayer and add a rule for search_knowledge_base: 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 RAD Security. Nothing to install.
search_knowledge_base 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_knowledge_base 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_knowledge_base. 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_knowledge_base is provided by the RAD Security MCP server (rad-security/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from RAD Security, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
55 RAD Security tools catalogued and risk-classified — across an index of 43,000+ MCP servers.