AI agents call zitadel_list_projects to retrieve information from Zitadel MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves project metadata from Zitadel without creating, modifying, deleting, or executing any operations. It is a straightforward query that returns information. The blast radius is minimal—listing projects exposes organizational structure but does not enable data modification or unauthorized access beyond what the authenticated user already has permission to view.
From the tool's definition Tool name 'zitadel_list_projects' and description 'List all projects in the Zitadel organization' indicate a retrieval operation with no side effects. The verb 'list' is explicitly a read operation per the guidelines.
Documented attack patterns abuse exactly the kind of access zitadel_list_projects gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Zitadel MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for zitadel_list_projects:
{
"version": "1",
"default": "deny",
"tools": {
"zitadel_list_projects": {}
}
} zitadel_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 Zitadel organization. It is categorised as a Read tool in the Zitadel MCP MCP Server, which means it retrieves data without modifying state.
Register the Zitadel MCP server in PolicyLayer and add a rule for zitadel_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 Zitadel MCP. Nothing to install.
zitadel_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 zitadel_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 zitadel_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.
zitadel_list_projects is provided by the Zitadel MCP server (takleb3rry/zitadel-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Zitadel MCP, 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.
26 Zitadel MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.