Skip to main content
Glama

network_create

Create a Docker network (bridge or overlay) to interconnect containers. Configure driver, IPAM, labels, and scope for your networking needs.

Instructions

Create a network.

The daemon default driver is bridge (single-host); use overlay for swarm-wide networks. Creating a network attaches nothing — connect containers afterwards with network_connect or at start via container_run(network=...). Created networks are stamped with provenance labels (find them later via network_list(managed_only=True)).

args: name - The name of the network driver - Driver name (daemon default bridge; overlay for swarm scope) options - Driver-specific options dict ipam - IPAM configuration as a dict (engine shape: {"Driver", "Config": [{"Subnet", "Gateway", ...}]}) check_duplicate - Reject creation if a duplicate name exists (deprecated: recent daemons always check) internal - Restrict external access labels - Labels to set on the network enable_ipv6 - Enable IPv6 networking attachable - Allow standalone containers to attach (swarm overlay networks) scope - Network scope: "local", "global", or "swarm" ingress - Make this an ingress network for swarm routing-mesh returns: dict - The created network's attrs (Id, Name, Driver, Scope, IPAM)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ipamNo
nameYes
scopeNo
driverNo
labelsNo
ingressNo
optionsNo
internalNo
attachableNo
enable_ipv6No
check_duplicateNo
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses that the tool only creates an empty network (no attachment), mentions default driver, provenance labels, and deprecated behavior of check_duplicate. Annotations already indicate non-destructive, so description adds needed context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Structured with intro, context paragraph, and parameter list, but the args section is lengthy and could be more concise. Every sentence adds value, but overall density is moderate.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers the creation process, return value format, and key details like provenance labels. No output schema exists, but the description sufficiently explains what the tool returns. Lacks only deeper parameter examples.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Lists all 11 parameters with some added meaning (e.g., ipam shape, scope enum), but many (like options, labels) get only minimal descriptions ('Driver-specific options dict') without further detail. With 0% schema coverage, the description helps but remains somewhat superficial.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Create a network' and distinguishes from siblings like network_connect and network_list by explaining that creating attaches nothing and that connecting is separate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises when to use bridge vs overlay, and directs to use network_connect or container_run for attaching containers. Also hints at finding networks with network_list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/L337-org/docker-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server