Search YOUR journal. Filters by entry_type, tags, and/or a semantic query (embedded via the configured embedding model, ranked by cosine similarity). By default scopes to YOUR agent_id; pass inherit_from=<predecessor_agent_id> to read a predecessor model\
AI agents call journal_recall 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.
journal_recall is a retrieval tool that queries a personal journal database with semantic search capabilities. It has no side effects—it does not create, modify, delete, or execute external operations. The ability to pass inherit_from to read a predecessor agent's journal is still a read operation scoped by agent context. The default scope to 'YOUR agent_id' ensures data isolation.
From the tool's definition The tool 'Search YOUR journal' with 'filters by entry_type, tags, and/or a semantic query' and 'ranked by cosine similarity' demonstrates retrieval and querying of existing data without modification.
Documented attack patterns abuse exactly the kind of access journal_recall 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_recall:
{
"version": "1",
"default": "deny",
"tools": {
"journal_recall": {}
}
}journal_recall 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.
Search YOUR journal. Filters by entry_type, tags, and/or a semantic query (embedded via the configured embedding model, ranked by cosine similarity). By default scopes to YOUR agent_id; pass inherit_from=<predecessor_agent_id> to read a predecessor model\. 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_recall: 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_recall 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_recall 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_recall. 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_recall 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.