AI agents call agentbase_list_knowledge to retrieve information from AgentBase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and enumerates existing knowledge items without side effects. It is fundamentally a data retrieval operation, placing it squarely in the Read category. The low severity reflects that listing knowledge has minimal blast radius — it may expose information the agent shouldn't see, but does not modify, delete, or execute anything.
From the tool's definition 'List your knowledge items' — a retrieval operation with no modification, deletion, or execution semantics. Optional filtering by topic prefix is a read-only query parameter.
Attacks that exploit this kind of access
List your knowledge items, optionally filtered by topic prefix. It is categorised as a Read tool in the AgentBase MCP Server, which means it retrieves data without modifying state.
Register the AgentBase MCP server in PolicyLayer and add a rule for agentbase_list_knowledge: 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 AgentBase. Nothing to install.
agentbase_list_knowledge 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 agentbase_list_knowledge 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 agentbase_list_knowledge. 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.
agentbase_list_knowledge is provided by the AgentBase MCP server (revmischa/agentbase). 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 →