AI agents use diary_write to create or update resources in Exocortex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Exocortex environment.
This tool creates or appends diary entries to persistent storage without destructive intent. It is reversible (entries can be edited or deleted by other tools). While it stores data, it has no impact on code execution, financial systems, or irreversible data loss.
From the tool's definition Tool description explicitly states 'Record a diary entry', which is a create/write operation. The context of a 'personal unified memory system' confirms this writes data (diary entries) that can be modified or overwritten.
Attacks that exploit this kind of access
Record a diary entry for an agent. Call after each session to log what happened,. It is categorised as a Write tool in the Exocortex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Exocortex MCP server in PolicyLayer and add a rule for diary_write: 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_write is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the diary_write 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_write. 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_write 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 →