AI agents call agentbase_search 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 retrieves data from a knowledge base. It does not create, modify, delete, or execute operations. The search is read-only against public knowledge, presenting minimal risk even if misused by an agent—worst case being retrieval of unintended information already marked public.
From the tool's definition Tool performs 'semantic search across all public knowledge using natural language' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Semantic search across all public knowledge using natural language. 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_search: 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_search 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_search 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_search. 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_search 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 →