Atlas — return a ranked list of recommended models with cost estimates for a given task description (POST ${ATLAS_URL}/v1/recommend). Atlas scores all catalog models for the task type and returns the top candidates with their per-1K input/output USD cost, so callers can pick on the cost/quality f...
AI agents call atlas_recommend 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 queries a catalog to fetch recommendations and cost data. It performs no writes, deletions, code execution, or financial transactions. While it exposes cost information, accessing cost estimates is informational read-only activity, not a financial operation that moves money or creates obligations.
From the tool's definition Tool returns 'a ranked list of recommended models with cost estimates' — it retrieves and ranks information from a catalog without modifying data.
Documented attack patterns abuse exactly the kind of access atlas_recommend 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 atlas_recommend:
{
"version": "1",
"default": "deny",
"tools": {
"atlas_recommend": {}
}
}atlas_recommend 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.
Atlas — return a ranked list of recommended models with cost estimates for a given task description (POST ${ATLAS_URL}/v1/recommend). Atlas scores all catalog models for the task type and returns the top candidates with their per-1K input/output USD cost, so callers can pick on the cost/quality frontier. 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 atlas_recommend: 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.
atlas_recommend 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 atlas_recommend 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 atlas_recommend. 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.
atlas_recommend 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.