mcp-podman-crunchtools
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PODMAN_SOCKET | No | Unix socket path | Auto-detect |
| PODMAN_TIMEOUT | No | Request timeout in seconds | 30 |
| PODMAN_SOCKET_FILE | No | File containing socket path |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| container_list_toolC | List containers. |
| container_inspect_toolC | Get detailed information about a container. |
| container_start_toolB | Start a stopped container. |
| container_stop_toolC | Stop a running container. |
| container_restart_toolC | Restart a container. |
| container_kill_toolC | Send a signal to a container. |
| container_rm_toolC | Remove a container. |
| container_logs_toolC | Get container logs. |
| container_top_toolB | List processes running inside a container. |
| container_stats_toolB | Get container resource usage statistics. |
| container_create_toolC | Create a new container. |
| container_prune_toolA | Remove all stopped containers. Returns: List of removed container IDs and reclaimed space |
| image_list_toolC | List images. |
| image_inspect_toolC | Get detailed information about an image. |
| image_pull_toolB | Pull an image from a registry. |
| image_rm_toolC | Remove an image. |
| image_prune_toolA | Remove unused images, like With no arguments only dangling (untagged, unused) images are removed. |
| pod_list_toolC | List pods. |
| pod_inspect_toolC | Get detailed information about a pod. |
| pod_start_toolC | Start a pod and all its containers. |
| pod_stop_toolC | Stop a pod and all its containers. |
| pod_restart_toolB | Restart a pod and all its containers. |
| pod_rm_toolB | Remove a pod and all its containers. |
| pod_create_toolC | Create a new pod. |
| network_list_toolC | List networks. |
| network_inspect_toolC | Get detailed information about a network. |
| volume_list_toolC | List volumes. |
| volume_inspect_toolC | Get detailed information about a volume. |
| system_info_toolA | Get Podman system information. Returns: System details including version, storage, registries, and runtime |
| system_df_toolA | Get Podman disk usage. Returns: Disk usage by images, containers, and volumes |
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 30 tools
Each tool targets a clearly distinct resource and action, e.g., container stop vs kill vs prune vs rm are unambiguous. Pod, image, network, volume, and system operations are also well separated with no meaningful overlap.
All 30 tools follow a consistent snake_case resource_action_tool pattern, such as container_list_tool, pod_create_tool, and image_pull_tool. The uniform suffix and verb placement make the naming predictable throughout.
With 30 tools, the server exceeds the recommended range and feels over-granular for an MCP surface. Although Podman has a broad domain, several operations could be consolidated or grouped to reduce the tool count.
Core container, pod, and image lifecycle operations are covered, but notable gaps remain: no network or volume creation/removal, no image build/push, no container exec, and no pod pause/unpause. These missing operations limit common Podman workflows.