Skip to main content
Glama

plugin_create

Create and install a local Docker plugin from a directory containing config.json and rootfs, optionally gzipped.

Instructions

Build a plugin from a local plugin data directory and install it under name.

The counterpart to plugin_install, which pulls an already-published plugin from a registry: use this only for a plugin rootfs you built yourself, and plugin_install for anything on a registry. plugin_data_dir is read on the machine running this server (not on the daemon host), must already contain a config.json manifest and a rootfs directory, and is tarred client-side and posted to the daemon — in a container it must be a bind mount or the path resolves to nothing. The new plugin is created disabled: call plugin_configure for any settings it declares, then plugin_enable to activate it. Raises if the directory is missing or lacks config.json/rootfs, or if name is already installed (remove it first with plugin_remove). Unlike the other create tools, this stamps no provenance labels — the Engine API's plugin-create call accepts none.

args: name - Local name for the plugin, author/name:tag; the :latest tag is optional and is the default if omitted plugin_data_dir - Path on this server's filesystem to the plugin data directory (containing config.json and rootfs) gzip - Compress the uploaded directory with gzip (default False) returns: dict - The created plugin's attrs ({"Id", "Name", "Enabled", "Settings", "Config"})

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
gzipNo
nameYes
plugin_data_dirYes
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses crucial behaviors: the plugin is created disabled, errors are raised for missing directories or duplicate names, no provenance labels are stamped, and plugin_data_dir is read client-side (not on the daemon host). These details are not inferable from annotations and materially affect tool usage.

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

Conciseness5/5

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

The description is front-loaded with a crisp purpose sentence, followed by a compact but dense paragraph of behavioral context, and then a clean args/returns section. Every sentence adds value—no filler, redundancy, or restatement of the tool name.

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

Completeness5/5

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

With no output schema and sparse parameter descriptions, the description carries the full burden. It includes the return dict fields, preconditions, error conditions, lifecycle steps, and the distinction from the sibling plugin_install tool. This is as complete as an agent needs for correct invocation.

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

Parameters5/5

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

The input schema has 0% description coverage, but the description fully compensates. It explains the name format (`author/name:tag` with optional `:latest`), specifies that plugin_data_dir must contain config.json and rootfs and is read on the server's filesystem, and clarifies gzip's role and default. This adds substantial meaning beyond the bare schema.

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?

The first sentence states a specific verb ('Build') and resource ('plugin from a local plugin data directory and install it under name'). It explicitly distinguishes this from plugin_install, which pulls an already-published plugin from a registry, making it clear among sibling plugin tools.

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?

The description gives explicit guidance: use this only for a self-built rootfs, use plugin_install for anything on a registry. It also provides prerequisites (config.json and rootfs required), container bind-mount requirement, and a clear lifecycle sequence: plugin_configure then plugin_enable.

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