AI agents call codex_list_project_api_keys 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 is a Read operation (retrieves/queries data without side effects). However, the severity is high because the tool exposes API keys, which are sensitive credentials that could be misused if an AI agent obtains and exfiltrates them. While the tool itself performs only a harmless read, the data it returns (API keys) has significant security implications if compromised.
From the tool's definition Tool name contains 'list' and description states 'List API keys associated with a project' — a retrieval operation with no modification.
Documented attack patterns abuse exactly the kind of access codex_list_project_api_keys 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_project_api_keys:
{
"version": "1",
"default": "deny",
"tools": {
"codex_list_project_api_keys": {}
}
}codex_list_project_api_keys 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 API keys associated with 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_project_api_keys: 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_project_api_keys 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_project_api_keys 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_project_api_keys. 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_project_api_keys 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.