Atlas — OpenAI-compatible chat completions through atlas.celiums.ai (POST ${ATLAS_URL}/v1/chat/completions). Atlas auto-routes to the optimal model unless \
AI agents invoke atlas_chat to trigger actions in Celiums Memory. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool sends requests to an external AI inference endpoint, triggering LLM completions via HTTP POST. It executes external operations whose effects depend on the arguments passed (prompts, model selection, etc.).
From the tool's definition OpenAI-compatible chat completions through atlas.celiums.ai (POST ${ATLAS_URL}/v1/chat/completions). Atlas auto-routes to the optimal model
Documented attack patterns abuse exactly the kind of access atlas_chat 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_chat:
{
"version": "1",
"default": "deny",
"tools": {
"atlas_chat": {
"limits": [
{
"counter": "atlas_chat_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}atlas_chat stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Atlas — OpenAI-compatible chat completions through atlas.celiums.ai (POST ${ATLAS_URL}/v1/chat/completions). Atlas auto-routes to the optimal model unless \. It is categorised as a Execute tool in the Celiums Memory MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Celiums Memory MCP server in PolicyLayer and add a rule for atlas_chat: 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_chat is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the atlas_chat 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_chat. 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_chat 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.