AI agents call agentbase_get_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 performs a straightforward data retrieval operation with no side effects. It queries a knowledge base by ID and returns either publicly available or user-owned items. The action is read-only and non-destructive, fitting the Read category. Severity is low because retrieving knowledge items from a shared base poses minimal risk even if misused by an agent.
From the tool's definition Tool name and description indicate retrieval only: 'Get a knowledge item by ID' with 'Returns public items for anyone, or your own private items.' No modification, deletion, or execution occurs.
Attacks that exploit this kind of access
Get a knowledge item by ID. Returns public items for anyone, or your own private items. 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_get_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_get_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_get_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_get_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_get_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 →