AI agents call dokploy_list_instances to retrieve information from Dokploy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and returns existing configuration data (instance names and URLs). It performs no modifications, deletions, or external operations. The disclosure of instance URLs poses minimal risk as these are pre-configured system details necessary for tool operation. This is a standard discovery/enumeration tool typical of management interfaces.
From the tool's definition Tool description states "List all configured Dokploy instances. Returns instance names and URLs" - a pure retrieval operation with no side effects.
Attacks that exploit this kind of access
List all configured Dokploy instances. Returns instance names and URLs. Use this to discover valid instance names for other tools. It is categorised as a Read tool in the Dokploy MCP Server, which means it retrieves data without modifying state.
Register the Dokploy MCP server in PolicyLayer and add a rule for dokploy_list_instances: 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 Dokploy. Nothing to install.
dokploy_list_instances 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 dokploy_list_instances 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 dokploy_list_instances. 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.
dokploy_list_instances is provided by the Dokploy MCP server (wyattjoh/dokploy-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 →