AI agents call teams to retrieve information from Coolify without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
All described operations are read-only queries: listing teams, getting current team, retrieving members. No write, execute, or destructive actions are mentioned. Severity is low as this only exposes organizational/membership data.
From the tool's definition list/current/current_members/get/members — all operations are retrieval-oriented (list, get, current, members)
Attacks that exploit this kind of access
Manage teams: list/current/current_members/get/members. It is categorised as a Read tool in the Coolify MCP Server, which means it retrieves data without modifying state.
Register the Coolify MCP server in PolicyLayer and add a rule for teams: 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 Coolify. Nothing to install.
teams 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 teams 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 teams. 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.
teams is provided by the Coolify MCP server (jurislm/coolify-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →