AI agents call codex_list_service_accounts 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 queries and returns service accounts, which is a read operation. However, service account credentials are security-sensitive information; exposing a list of them to an unauthorized or compromised AI agent could enable privilege escalation or lateral movement attacks.
From the tool's definition Tool name contains 'list' and description states 'List service accounts for a project' — a retrieval operation with no modification.
Documented attack patterns abuse exactly the kind of access codex_list_service_accounts 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_list_service_accounts:
{
"version": "1",
"default": "deny",
"tools": {
"codex_list_service_accounts": {}
}
}codex_list_service_accounts 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.
List service accounts for a project. 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_list_service_accounts: 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_list_service_accounts 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_list_service_accounts 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_list_service_accounts. 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_list_service_accounts 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.