kb_list
AI agents call kb_list to retrieve information from Knowledge Base MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'list' operation is fundamentally a read action that queries and returns data from the knowledge base. The empty description limits confidence slightly, but the semantic naming convention and server context (persistent knowledge storage and retrieval) make it clear this queries rather than modifies or executes.
From the tool's definition Tool name 'kb_list' indicates a listing/retrieval operation. No destructive, financial, or executable operations are implied.
Attacks that exploit this kind of access
kb_list. It is categorised as a Read tool in the Knowledge Base MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Knowledge Base MCP Server MCP server in PolicyLayer and add a rule for kb_list: 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 Knowledge Base MCP Server. Nothing to install.
kb_list 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 kb_list 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 kb_list. 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.
kb_list is provided by the Knowledge Base MCP Server MCP server (leon4s4/knowledge-base-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
kb_list is one line of Knowledge Base MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →