AI agents call support_knowledge_base to retrieve information from AgentOS without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a knowledge base and returns information without side effects. It matches the Read category pattern of retrieval operations (search, fetch, get). The severity is low because misuse would only surface irrelevant or excessive search results, with no risk to data integrity, financial systems, or external operations.
From the tool's definition Tool description states 'Search the knowledge base for help articles and FAQs' — a retrieval operation with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Search the knowledge base for help articles and FAQs. It is categorised as a Read tool in the AgentOS MCP Server, which means it retrieves data without modifying state.
Register the AgentOS MCP server in PolicyLayer and add a rule for support_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 AgentOS. Nothing to install.
support_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 support_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 support_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.
support_knowledge_base is provided by the AgentOS MCP server (netflypsb/agentos). 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 →