MCP server enabling AI assistants to execute terminal commands through a secure shell interface
MCP server enabling AI assistants to execute terminal commands through a secure shell interface. The pandora's shell mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 8 defined tools rather than through you.
⚠️ IMPORTANT SECURITY WARNING: This MCP server grants AI assistants unrestricted ability to execute terminal commands on your system. Only use in controlled environments like virtual machines (VMs) or development systems you can afford to rebuild.
An MCP server that empowers AI assistants to execute terminal commands on your system. Due to the unrestricted access this provides, it's crucial to use this software responsibly and be fully aware of the security risks involved.
mcp on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Everything the assistant can do here goes through one of these:
execute_command — Execute any shell command and return its outputInputs — - command (string): Command to executeReturns — - Command exit codeFeatures — - 5-minute timeoutTools — The Tools tool exposed by this serverPrerequisites — The Prerequisites tool exposed by this serverWindows — Locate the correct configuration directory - try these paths in order:macOS — Create or edit ~/Library/Application Support/Claude/claude_desktop_config.json:You will need one environment variable: PYTHONPATH. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the file and storage access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Pandora'S Shell's toolset — execute_command, Inputs, Returns and 5 more — is a fair guide to whether it matches your workflow. It is maintained by Zelaron; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| execute_command | Execute any shell command and return its output |
| Inputs | - command (string): Command to execute |
| Returns | - Command exit code |
| Features | - 5-minute timeout |
| Tools | The Tools tool exposed by this server. |
| Prerequisites | The Prerequisites tool exposed by this server. |
| Windows | Locate the correct configuration directory - try these paths in order: |
| macOS | Create or edit ~/Library/Application Support/Claude/claude_desktop_config.json: |
{
"mcpServers": {
"pandoras-shell": {
"command": "uvx",
"args": ["mcp"],
"env": {
"PYTHONPATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| PYTHONPATH | Filesystem location the server is allowed to use. | Optional |
Scoped local file access — read, write, search and reorganise files in directories you explicitly allow.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Connects AI models to an Obsidian knowledge base for direct access and manipulation of notes and folders.