QuixiAI/dolphin-mcp

A flexible Python library and CLI tool for interacting with Model Context Protocol (MCP) servers using any LLM model.
## Overview
Dolphin MCP is both a Python library and a command-line tool that allows you to query and interact with MCP servers through natural language. It connects to any number of configured MCP servers, makes their tools available to language models (OpenAI, Anthropic, Ollama, LMStudio), and provides a conversational interface for accessing and manipulating data from these servers.
The project demonstrates how to:
Connect to multiple MCP servers simultaneously
List and call tools provided by these servers
Use function calling capabilities to interact with external data sources
Process and present results in a user-friendly way
Create a reusable Python library with a clean API
Build a command-line interface on top of the library
## Features
Multiple Provider Support: Works with OpenAI, Anthropic, Ollama, and LMStudio models
Modular Architecture: Clean separation of concerns with provider-specific modules
Dual Interface: Use as a Python library or command-line tool
MCP Server Integration: Connect to any number of MCP servers simultaneously
Tool Discovery: Automatically discover and use tools provided by MCP servers
Flexible Configuration: Configure models and servers through JSON configuration
Environment Variable Support: Securely store API keys in environment variables
Comprehensive Documentation: Detailed usage examples and API documentation
Installable Package: Easy installation via pip with dolphin-mcp-cli command
## Prerequisites
Before installing Dolphin MCP, ensure you have the following prerequisites installed:
1. Python 3.10+
2. SQLite - A lightweight database used by the demo
3. uv/uvx - A fast Python package installer and resolver
### Setting up Prerequisites
#### Windows
1. Python 3.10+:
Download and install from python.org
Ensure you check "Add Python to PATH" during installation
2. SQLite:
Download the precompiled binaries from SQLite website
Choose the "Precompiled Binaries for Windows" section and download the sqlite-tools zip file
Extract the files to a folder (e.g., C:\sqlite)
Add this folder to your PATH:
Open Control Panel > System > Advanced System Settings > Environment Variables
Edit the PATH variable and add the path to your SQLite folder
Verify installation by opening Command Prompt and typing sqlite3 --version
3. uv/uvx:
Open PowerShell as Administrator and run:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Restart your terminal and verify installation with uv --version
#### macOS
1. Python 3.10+:
Install using Homebrew:
brew install python
2. SQLite:
SQLite comes pre-installed on macOS, but you can update it using Homebrew:
brew install sqlite
Verify installation with sqlite3 --version
3. uv/uvx:
Install using Homebrew:
brew install uv
Or use the official installer:
curl -LsSf https://astral.sh/uv/install.sh | sh
Verify installation with uv --version
#### Linux (Ubuntu/Debian)
1. Python 3.10+:
sudo apt update
sudo apt install python3 python3-pip
2. SQLite:
sudo apt update
sudo apt install sqlite3
Verify installation with sqlite3 --version
3. uv/uvx: