Run after-LLM side effects for the just-completed turn. Stores an episodic memory (auto-capture), boosts importance of the prior reply if the user reinforced (proactiveCultivate), and fires a synthesize on rich turns (decisions, milestones). Daily caps: cultivate 5/day, synthesize 3/day per (user...
AI agents use turn_after to create or update resources in Celiums Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Celiums Memory environment.
This tool primarily writes data — it stores episodic memories, updates importance scores, and triggers synthesis. All of these create or modify persistent memory records. While it triggers side effects, these are data persistence operations rather than code execution or irreversible deletions. The 'synthesize' firing and 'cultivate' boosts are write-level operations updating memory state.
From the tool's definition Stores an episodic memory (auto-capture), boosts importance of the prior reply if the user reinforced (proactiveCultivate), and fires a synthesize on rich turns (decisions, milestones)
Documented attack patterns abuse exactly the kind of access turn_after gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Celiums Memory, and nothing reaches the server without passing your rules. This is the rule we recommend for turn_after:
{
"version": "1",
"default": "deny",
"tools": {
"turn_after": {
"limits": [
{
"counter": "turn_after_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}turn_after stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run after-LLM side effects for the just-completed turn. Stores an episodic memory (auto-capture), boosts importance of the prior reply if the user reinforced (proactiveCultivate), and fires a synthesize on rich turns (decisions, milestones). Daily caps: cultivate 5/day, synthesize 3/day per (user,conversation). Updates the failure flag for next turn\. It is categorised as a Write tool in the Celiums Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Celiums Memory MCP server in PolicyLayer and add a rule for turn_after: 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 Celiums Memory. Nothing to install.
turn_after 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 turn_after 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 turn_after. 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.
turn_after is provided by the Celiums Memory MCP server (terrizoaguimor/celiums-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Celiums Memory, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
62 Celiums Memory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.