AI agents use post_session to create or update resources in Tages — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tages environment.
This tool creates and modifies stored memories and project briefs based on session input. These are Write operations because they create new records and update existing documentation without permanently destroying data (memories and briefs can be revised, archived, or corrected in future sessions).
From the tool's definition Tool description states it will 'extract memories from a session summary' and 'optionally regenerate the project brief' — both operations that create or modify data (in this case, persisted memory records and project documentation) in a reversible manner.
Attacks that exploit this kind of access
End-of-session tool: extract memories from a session summary, optionally regenerate the project brief. Combines session_end + brief regeneration in one call. It is categorised as a Write tool in the Tages MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tages MCP server in PolicyLayer and add a rule for post_session: 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 Tages. Nothing to install.
post_session 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 post_session 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 post_session. 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.
post_session is provided by the Tages MCP server (ryantlee25-droid/tages). 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 →