Build a coherent arc across YOUR recent entries using the configured LLM — with anti-confabulation guardrails. Output ALWAYS returns 4 keys: narrative, contradictions (entry pairs in tension), outliers (entries that don\
AI agents call journal_arc 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 reads and analyzes existing journal entries to synthesize a narrative arc. It retrieves and processes stored memory data without creating, modifying, or deleting anything. The anti-confabulation guardrails and fixed output keys reinforce that this is a read/analysis operation. Severity is low as it only surfaces the user's own stored data.
From the tool's definition Build a coherent arc across YOUR recent entries...Output ALWAYS returns 4 keys: narrative, contradictions, outliers
Documented attack patterns abuse exactly the kind of access journal_arc 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 journal_arc:
{
"version": "1",
"default": "deny",
"tools": {
"journal_arc": {}
}
}journal_arc 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.
Build a coherent arc across YOUR recent entries using the configured LLM — with anti-confabulation guardrails. Output ALWAYS returns 4 keys: narrative, contradictions (entry pairs in tension), outliers (entries that don\. 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 journal_arc: 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.
journal_arc 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 journal_arc 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 journal_arc. 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.
journal_arc 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.