Persistent Shell MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| execute_commandC | Execute a shell command in the background 'exec' window and return the output. |
| start_processB | Start a long-running or interactive process. Defaults to the background |
| get_outputA | Get current terminal output. Defaults to the |
| send_inputC | Send input to a running process in a specified window. |
| stop_processB | Stop the currently running process in the exec window (sends Ctrl+C). |
| create_workspaceC | Create a new isolated workspace for commands. |
| destroy_workspaceB | Destroy a workspace and all its processes. |
| list_workspacesB | List all active workspaces. |
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 8 tools
Each tool has a clearly distinct purpose with no ambiguity. For example, create_workspace/destroy_workspace handle workspace lifecycle, execute_command/start_process differentiate between one-off commands and long-running processes, and get_output/send_input separate output retrieval from input sending. The descriptions clearly delineate when to use each tool.
All tools follow a consistent verb_noun pattern with snake_case throughout. The naming convention is perfectly predictable: create_workspace, destroy_workspace, execute_command, get_output, list_workspaces, send_input, start_process, stop_process. This consistency makes the tool set easy to understand and navigate.
With 8 tools, this server is well-scoped for persistent shell management. Each tool earns its place by covering essential operations: workspace management (create/destroy/list), process execution (execute/start/stop), and I/O handling (get_output/send_input). The count is neither too sparse nor bloated for the domain.
The tool surface provides excellent coverage of core persistent shell operations, including workspace lifecycle, process management, and I/O. A minor gap exists in workspace modification (e.g., rename_workspace or update_workspace_settings), but agents can work around this by destroying and recreating workspaces. The tools support complete workflows without dead ends.