Compose the proactive turn-context blocks for the current user message. Composes 8 channels in parallel (identity priors + continuity briefing + auto-recalled memory + forage corpus + ethics-advisory + epistemic-flag + suggestion-intents + limbic PAD state) and returns JSON with
AI agents call turn_context to retrieve information from Celiums Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool assembles and retrieves contextual information (identity priors, memory recall, emotional state, ethics advisories, etc.) to inform the current conversational turn. It reads and composes data from multiple memory/state channels but does not modify, delete, or execute anything.
From the tool's definition Compose the proactive turn-context blocks... returns JSON with [8 channels of context data]
Documented attack patterns abuse exactly the kind of access turn_context 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_context:
{
"version": "1",
"default": "deny",
"tools": {
"turn_context": {}
}
}turn_context is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Compose the proactive turn-context blocks for the current user message. Composes 8 channels in parallel (identity priors + continuity briefing + auto-recalled memory + forage corpus + ethics-advisory + epistemic-flag + suggestion-intents + limbic PAD state) and returns JSON with. It is categorised as a Read tool in the Celiums Memory MCP Server, which means it retrieves data without modifying state.
Register the Celiums Memory MCP server in PolicyLayer and add a rule for turn_context: 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_context 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 turn_context 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_context. 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_context 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.