List Docker networks
AI agents call list_networks to retrieve information from Docker MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries Docker network configuration. It retrieves information about networks but has no side effects, matches the 'list' pattern (explicitly cited as a Read category example), and carries minimal risk if misused by an AI agent—returning network metadata cannot cause harm.
From the tool's definition Tool name is 'list_networks' and description states 'List Docker networks' - a query operation that retrieves and enumerates existing Docker networks without modifying or deleting anything.
Attacks that exploit this kind of access
List Docker networks. It is categorised as a Read tool in the Docker MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Docker MCP Server MCP server in PolicyLayer and add a rule for list_networks: 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 Docker MCP Server. Nothing to install.
list_networks 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 list_networks 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 list_networks. 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.
list_networks is provided by the Docker MCP Server MCP server (swartdraak/docker-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 →