AI agents call agentbase_introspect 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 reads and returns schema information without creating, modifying, deleting, or executing any operations. It is informational and poses minimal risk — typical use is to help agents understand available API operations. The schema itself is not sensitive data in this context and is explicitly stated as requiring 'no authentication', indicating it is public reference material.
From the tool's definition Tool name 'agentbase_introspect' and description 'Return the full AgentBase GraphQL schema for reference' indicate a retrieval operation that returns schema metadata. No side effects, authentication, or data modification occurs.
Attacks that exploit this kind of access
Return the full AgentBase GraphQL schema for reference. No authentication required. 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_introspect: 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_introspect 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_introspect 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_introspect. 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_introspect 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 →