shellserver
A Model Context Protocol server that exposes a tool to execute shell commands on the host machine, with customizable working directory and timeout.
README
shellserver
A small Model Context Protocol (MCP) server built with the Python MCP SDK (FastMCP). It exposes one tool that runs shell commands on the machine where the server process runs.
Requirements
- Python 3.14+ (see
pyproject.toml) - uv for installing and running dependencies
Setup
Clone or copy this repository, then from the project root:
uv sync
Running the server
The server uses stdio transport (the default for FastMCP).
uv run python server.py
Do not pipe extra data to stdout from the server process; MCP uses stdout for JSON-RPC. Logging in server.py is directed to stderr.
Tool: terminal_tool
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
command |
string | yes | — | Shell command to run |
cwd |
string | no | — | Working directory for the subprocess |
timeout_seconds |
number | no | 120 |
Seconds to wait before killing the process |
The tool returns a single text block containing exit_code, stdout, and stderr. If the command exceeds the timeout, the process is terminated and the response indicates a timeout.
Connecting a client (example of running locally)
Point your MCP host at uv with this project as the working directory. Example configuration shape:
{
"mcpServers": {
"shellserver": {
"command": "uv",
"args": ["run", "python", "server.py"],
"cwd": "/absolute/path/to/shellserver"
}
}
}
Adjust the key name and cwd to match your editor or client.
Security
This server executes arbitrary shell commands on the host. Anyone who can invoke MCP tools against this server effectively has shell access to that machine. Use only on trusted hosts, with trusted clients, and with clear understanding of the risk.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.