mcp-server-toolkit
A Model Context Protocol server providing LLM Agents with system utilities and tools, including IP geolocation, network diagnostics, system monitoring, cryptographic operations, and QR code generation.
What is mcp-server-toolkit?
mcp-server-toolkit is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol server providing llm agents with system utilities and tools, including ip geolocation, network diagnostics, system monitoring, cryptographic operations, and qr code generation....
A Model Context Protocol server providing LLM Agents with system utilities and tools, including IP geolocation, network diagnostics, system monitoring, cryptographic operations, and QR code generation.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- getCurrentTime
- getSystemInfo
- getLoadAverage
- getNetworkInterfaces
- checkConnectivity
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @cyanheads/toolkit-mcp-serverManual Installation
npx -y @cyanheads/toolkit-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use mcp-server-toolkit
mcp-server-toolkit is an extensible MCP server framework written in TypeScript/Python that provides LLM agents with system utilities, network diagnostics, cryptographic operations, IP geolocation, and QR code generation through a plugin architecture. It supports both stdio (local agent) and HTTP transports with optional API key or OAuth 2.1 authentication, per-client rate limiting, and OpenTelemetry observability. Developers can register custom tools via a decorator pattern and ship them alongside the bundled filesystem sandbox and external-API wrapper plugins.
Prerequisites
- Python 3.12 or newer
- uv package manager (https://github.com/astral-sh/uv)
- Git for cloning the repository
- An MCP-compatible AI client such as Claude Desktop or Claude Code
- Optional: MCP_SARMALINK_API_KEY if using the sarmalink external-API plugin
Clone the repository and install dependencies
Clone the project and use uv to sync the Python dependencies into an isolated virtual environment.
git clone https://github.com/sarmakska/mcp-server-toolkit.git
cd mcp-server-toolkit
uv syncCreate and configure the environment file
Copy the example environment file and set the variables relevant to your deployment. At minimum you can leave all defaults for a local stdio server.
cp .env.example .env
# Edit .env — key variables:
# MCP_TRANSPORT=stdio # or http
# MCP_AUTH=none # or api_key / oauth
# MCP_API_KEY=your-secret # required if MCP_AUTH=api_key
# MCP_FS_ROOT=~/mcp-data # sandbox directory for filesystem plugin
# MCP_SARMALINK_API_KEY=... # required if using sarmalink pluginStart the server in stdio mode
Launch the server over stdio for local agent use. This is the mode used when an MCP client starts the server as a subprocess.
uv run mcp-toolkit run --transport stdio(Optional) Start the server in HTTP mode
For remote or multi-client deployments, run the server over HTTP. The default port is 8000 and can be changed via MCP_HTTP_PORT.
uv run mcp-toolkit run --transport http --port 8000Add the server to your MCP client
Configure your AI client to launch the toolkit server as a stdio subprocess. Adjust the command path to match your cloned repository location.
{
"mcpServers": {
"toolkit": {
"command": "uv",
"args": ["run", "mcp-toolkit", "run", "--transport", "stdio"],
"cwd": "/path/to/mcp-server-toolkit",
"env": {
"MCP_FS_ROOT": "/Users/yourname/mcp-data"
}
}
}
}mcp-server-toolkit Examples
Client configuration
claude_desktop_config.json entry for running mcp-server-toolkit over stdio with a sandboxed filesystem root.
{
"mcpServers": {
"toolkit": {
"command": "uv",
"args": ["run", "mcp-toolkit", "run", "--transport", "stdio"],
"cwd": "/Users/yourname/mcp-server-toolkit",
"env": {
"MCP_FS_ROOT": "/Users/yourname/mcp-data",
"MCP_AUTH": "none"
}
}
}
}Prompts to try
Example prompts for the system utilities and network tools exposed by mcp-server-toolkit.
- "What is the current system load average and how many CPU cores does this machine have?"
- "Check my network interfaces and show me all active IP addresses"
- "Test connectivity to 8.8.8.8 and report latency"
- "Generate a SHA-256 hash of the string 'hello world'"
- "List all files in my mcp-data directory"Troubleshooting mcp-server-toolkit
Server exits immediately when started by MCP client
Run 'uv run mcp-toolkit run --transport stdio' directly in the terminal to see error output. The most common cause is a missing or malformed .env file — ensure .env exists in the project root. If using MCP_AUTH=api_key, confirm MCP_API_KEY is set.
Filesystem plugin tools fail with 'path outside sandbox' error
All file operations are restricted to the directory set by MCP_FS_ROOT (default: ~/mcp-data). Create this directory if it does not exist: 'mkdir -p ~/mcp-data'. To change the sandbox root, update MCP_FS_ROOT in your .env file or in the client configuration env block.
HTTP transport returns 401 Unauthorized
If MCP_AUTH is set to 'api_key', every request must include an Authorization header: 'Authorization: Bearer your-api-key'. Confirm the key in the request matches MCP_API_KEY in your .env file. Set MCP_AUTH=none to disable authentication for local development.
Frequently Asked Questions about mcp-server-toolkit
What is mcp-server-toolkit?
mcp-server-toolkit is a Model Context Protocol (MCP) server that model context protocol server providing llm agents with system utilities and tools, including ip geolocation, network diagnostics, system monitoring, cryptographic operations, and qr code generation. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install mcp-server-toolkit?
Install via npm with the command: npx -y @cyanheads/toolkit-mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with mcp-server-toolkit?
mcp-server-toolkit works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is mcp-server-toolkit free to use?
Yes, mcp-server-toolkit is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
mcp-server-toolkit Alternatives — Similar Developer Tools Servers
Looking for alternatives to mcp-server-toolkit? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up mcp-server-toolkit in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use mcp-server-toolkit?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.