LMStudio Toolpack
A MCP stdio toolpack for local LLMs
What is LMStudio Toolpack?
LMStudio Toolpack is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp stdio toolpack for local llms
A MCP stdio toolpack for local LLMs
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A MCP stdio toolpack for local LLMs
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx lmstudio-toolpackConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use LMStudio Toolpack
LMStudio Toolpack is a collection of three MCP stdio servers designed to augment local LLMs with real-world capabilities: web search via DuckDuckGo, sandboxed Python code execution (with NumPy and SymPy), and lightweight long-term memory. It is built with Python and managed via uv, making it straightforward to run alongside LM Studio or any MCP-compatible client. Developers building offline-first AI applications can use it to give their local models the ability to search the web, run computations, and retain notes across sessions.
Prerequisites
- Python 3.13 or later installed
- uv package manager installed (pip install uv or see docs.astral.sh/uv)
- LM Studio or any MCP-compatible client (Claude Desktop, Cursor, etc.)
- Optional: set PYTHON_SANDBOX_LOG_PATH if you want audit logs of sandbox executions
Clone the repository
Clone the lmstudio-toolpack repository to your local machine and enter the project directory.
git clone https://github.com/ZihaoFU245/lmstudio-toolpack.git
cd lmstudio-toolpackInstall dependencies with uv
Use uv to sync all Python dependencies declared in the project. Python 3.13+ is required.
uv syncRun the configuration wizard
Execute the main wizard to generate an mcp.json configuration file that your MCP client can consume. The wizard outputs stdio command/args entries for each of the three servers.
uv run python main.pyConfigure your MCP client
Add the generated server entries to your MCP client config. Below is an example for Claude Desktop referencing the Python sandbox server. Adjust the path to match your clone location.
{
"mcpServers": {
"python-sandbox": {
"command": "python",
"args": ["/path/to/lmstudio-toolpack/python-sandbox.py"],
"env": {
"PYTHON_SANDBOX_LOG_PATH": "/tmp/sandbox-audit.jsonl"
}
},
"web-search": {
"command": "python",
"args": ["/path/to/lmstudio-toolpack/web_search.py"]
},
"longterm-memory": {
"command": "python",
"args": ["/path/to/lmstudio-toolpack/longterm_memory.py"]
}
}
}Verify each server individually
You can start each server manually to confirm it launches without errors before connecting your client.
python python-sandbox.pyLMStudio Toolpack Examples
Client configuration
Claude Desktop configuration showing all three toolpack servers. Replace /path/to/lmstudio-toolpack with your actual clone path.
{
"mcpServers": {
"python-sandbox": {
"command": "python",
"args": ["/path/to/lmstudio-toolpack/python-sandbox.py"],
"env": {
"PYTHON_SANDBOX_LOG_PATH": "/tmp/sandbox-audit.jsonl"
}
},
"web-search": {
"command": "python",
"args": ["/path/to/lmstudio-toolpack/web_search.py"]
},
"longterm-memory": {
"command": "python",
"args": ["/path/to/lmstudio-toolpack/longterm_memory.py"]
}
}
}Prompts to try
Sample prompts that exercise the three servers after connecting your MCP client.
- "Search the web for the latest Python 3.14 release notes and summarize the key changes."
- "Run this Python code: import sympy; x = sympy.Symbol('x'); print(sympy.diff(x**3 + 2*x, x))"
- "Remember that my project deadline is June 30th so you can refer to it later."
- "What notes do you have stored in long-term memory about my projects?"Troubleshooting LMStudio Toolpack
uv sync fails with 'Python 3.13 not found'
Install Python 3.13+ via your system package manager or from python.org, then re-run uv sync. You can also use 'uv python install 3.13' if your uv version supports it.
Python sandbox server crashes when executing code with NumPy
Ensure uv sync completed successfully and all optional dependencies were installed. Run 'uv run python -c "import numpy"' to verify the environment is intact.
MCP client cannot connect to the server
Confirm the path to each .py file in your config is an absolute path. Check that the Python executable used in the command field matches the one in your uv virtual environment (typically .venv/bin/python).
Frequently Asked Questions about LMStudio Toolpack
What is LMStudio Toolpack?
LMStudio Toolpack is a Model Context Protocol (MCP) server that mcp stdio toolpack for local llms It connects AI assistants to external tools and data sources through a standardized interface.
How do I install LMStudio Toolpack?
Follow the installation instructions on the LMStudio Toolpack GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with LMStudio Toolpack?
LMStudio Toolpack works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is LMStudio Toolpack free to use?
Yes, LMStudio Toolpack is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
LMStudio Toolpack Alternatives — Similar Developer Tools Servers
Looking for alternatives to LMStudio Toolpack? 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 LMStudio Toolpack 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 LMStudio Toolpack?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.