Container Exec MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP server port | 4200 |
| MCP_AUTH_TOKEN | No | Authentication token for HTTP server (optional) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| execC | Execute a command in a Docker container |
| list_containersA | List Docker containers. By default shows only running containers, use all=true to show all containers including stopped ones. |
| get_container_infoA | Get detailed information about a specific Docker container including state, network, mounts, environment, and resource configuration. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: exec for command execution, get_container_info for detailed container metadata, and list_containers for container enumeration. There is no overlap in functionality, making tool selection straightforward for an agent.
Two tools follow a consistent verb_noun pattern (get_container_info, list_containers), but exec uses a standalone verb without a noun. While the naming is readable and mostly consistent, the deviation from the pattern slightly reduces predictability.
Three tools are reasonable for a Docker container management server, covering core operations like listing, inspecting, and executing commands. However, the scope feels slightly thin, as common operations like starting/stopping containers or managing images are missing, though not critically so.
The toolset covers basic read and execute operations (list, get, exec) but lacks lifecycle management tools such as start, stop, create, or delete containers. This creates notable gaps that agents may need to work around, limiting full container management workflows.