Get embeddings usage data for the organization, broken down by time buckets and optional grouping dimensions
AI agents call codex_get_embeddings_usage to retrieve information from Sage MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves usage statistics and metrics for embeddings. It is purely a query/read operation that returns observability data about organizational resource consumption. There is no data modification, deletion, code execution, or financial transaction involved. The only risk is potential information disclosure of usage patterns, which is low severity in a properly access-controlled environment.
From the tool's definition Tool name contains 'get' and description states 'Get embeddings usage data' — a retrieval operation that queries existing data without modification or side effects.
Documented attack patterns abuse exactly the kind of access codex_get_embeddings_usage gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sage MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for codex_get_embeddings_usage:
{
"version": "1",
"default": "deny",
"tools": {
"codex_get_embeddings_usage": {}
}
}codex_get_embeddings_usage 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.
Get embeddings usage data for the organization, broken down by time buckets and optional grouping dimensions. It is categorised as a Read tool in the Sage MCP MCP Server, which means it retrieves data without modifying state.
Register the Sage MCP server in PolicyLayer and add a rule for codex_get_embeddings_usage: 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 Sage MCP. Nothing to install.
codex_get_embeddings_usage 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 codex_get_embeddings_usage 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 codex_get_embeddings_usage. 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.
codex_get_embeddings_usage is provided by the Sage MCP server (sagemcp/sagemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 359 Sage MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
359 Sage MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.