AI agents call diary_list_agents to retrieve information from Exocortex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves metadata about agents and their diary statistics without modifying any data or triggering external operations. It is a simple informational query with minimal blast radius if misused by an agent—worst case would be exposure of which agents exist and their activity patterns. This fits squarely into the Read category.
From the tool's definition Tool name contains 'list' and description states 'List all agents that have diary entries, with entry counts and last entry date.' This is purely a query/retrieval operation with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
List all agents that have diary entries, with entry counts and last entry date. It is categorised as a Read tool in the Exocortex MCP Server, which means it retrieves data without modifying state.
Register the Exocortex MCP server in PolicyLayer and add a rule for diary_list_agents: 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 Exocortex. Nothing to install.
diary_list_agents 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 diary_list_agents 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 diary_list_agents. 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.
diary_list_agents is provided by the Exocortex MCP server (shawnhack/exocortex). 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 →