MCPgee
MCPgee
MCPgeeMCPgee

MCPStack

v1.0.0•Developer Tools•stable

Stack & Orchestrate MCP Tools — The Scikit-Learn-Pipeline Way , For LLMs

llmsmcpmcp-toolsmodel-context-protocolopen-science
Share:
16
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is MCPStack?

MCPStack is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to stack & orchestrate mcp tools — the scikit-learn-pipeline way , for llms

Stack & Orchestrate MCP Tools — The Scikit-Learn-Pipeline Way , For LLMs

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Stack & Orchestrate MCP Tools — The Scikit-Learn-Pipeline Wa

Use Cases

Orchestrate multiple MCP tools like a machine learning pipeline.
Stack and compose MCP tools for complex LLM workflows.
MCP-Pipeline

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedJan 5, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx mcpstack

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCPStack

MCPStack is a Python framework for orchestrating multiple MCP tools into composable pipelines, inspired by the scikit-learn Pipeline API. Instead of calling MCP tools individually, you chain them together in a typed sequence where the output of one tool feeds as input to the next — enabling complex multi-step LLM workflows with minimal boilerplate. It provides a CLI for listing available tools, configuring presets, building pipelines, and deploying them to Claude Desktop or other LLM environments via FastMCP.

Prerequisites

  • Python 3.9+ installed
  • uv package manager (recommended) or pip for installation
  • MCP-compatible tools you want to orchestrate already configured
  • Claude Desktop or another MCP client to deploy pipelines to (optional)
  • Familiarity with the scikit-learn Pipeline concept is helpful
1

Install MCPStack

Install MCPStack using uv (recommended for speed) or pip.

# Using uv (recommended)
uv add mcpstack

# Using pip
pip install mcpstack
2

List available MCP tools

Use the mcpstack CLI to discover what tools are available in your environment before building a pipeline.

mcpstack list-tools
3

Configure individual tools

Configure each tool you want to include in your pipeline using the tools configure subcommand. This lets you pre-set tool parameters and behavior before assembly.

mcpstack tools <tool_name> configure <flags>
4

Create and build a pipeline

Create a new pipeline with the pipeline subcommand, then build it into a deployable format. Specify the config type for your target client (e.g., claude-desktop).

mcpstack pipeline <tool_name> --new
mcpstack build --pipeline <path-to-pipeline> --config-type claude-desktop
5

Run the pipeline programmatically

Alternatively, use MCPStack's Python API to build and run pipelines in code — similar to how you chain sklearn transformers.

from mcpstack import Pipeline

pipeline = (
    Pipeline()
    .with_tool("fetch_webpage")
    .with_tool("summarize_text")
    .with_tool("translate_to_french")
    .build()
)
result = pipeline.run(input="https://example.com")

MCPStack Examples

Client configuration

MCP client configuration for running MCPStack as an MCP server that exposes assembled pipelines.

{
  "mcpServers": {
    "mcpstack": {
      "command": "python",
      "args": ["-m", "mcpstack.server"],
      "env": {}
    }
  }
}

Prompts to try

Example prompts for working with MCPStack pipelines.

- "List all available MCP tools in my MCPStack environment."
- "Build an MCPStack pipeline that fetches a URL, extracts the main text, and then summarizes it in three bullet points."
- "Show me the preset pipelines available in MCPStack and explain what each one does."
- "Help me write a Python script using MCPStack to orchestrate a data-cleaning and classification pipeline."

Troubleshooting MCPStack

mcpstack command not found after installation

If using uv, run 'uv run mcpstack list-tools' to ensure the command runs in the project's virtual environment. With pip, confirm that the Python Scripts directory is on your PATH by running 'python -m mcpstack list-tools'.

Pipeline build fails with missing tool errors

Run 'mcpstack list-tools' to confirm all referenced tools are discoverable. Each tool must be configured and available in your MCP environment before it can be included in a pipeline. Check that any upstream MCP servers are running.

Pipeline produces unexpected output when chaining tools

Debug by running tools individually first to verify their standalone output. MCPStack pipelines pass outputs directly as inputs to the next stage, so verify that the output schema of each tool matches the expected input of the next.

Frequently Asked Questions about MCPStack

What is MCPStack?

MCPStack is a Model Context Protocol (MCP) server that stack & orchestrate mcp tools — the scikit-learn-pipeline way , for llms It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCPStack?

Follow the installation instructions on the MCPStack GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with MCPStack?

MCPStack works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCPStack free to use?

Yes, MCPStack is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

MCPStack Alternatives — Similar Developer Tools Servers

Looking for alternatives to MCPStack? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 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

★ 104.5k

A 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

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A 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.

Developer ToolsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "mcpstack": { "command": "npx", "args": ["-y", "mcpstack"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MCPStack?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides