AI agents call codex_list_projects 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 and enumerates projects within an organization with no side effects. It is a straightforward read operation. Severity is low because listing projects is informational; the blast radius of misuse is limited to information disclosure of project metadata, which typically has low impact in organizational contexts.
From the tool's definition Tool name 'codex_list_projects' and description 'List all projects in the organization' indicate a query operation that retrieves data without modification.
Documented attack patterns abuse exactly the kind of access codex_list_projects 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_projects:
{
"version": "1",
"default": "deny",
"tools": {
"codex_list_projects": {}
}
}codex_list_projects 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 all projects in the organization. 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_projects: 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_projects 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_projects 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_projects. 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_projects 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.