{"type":"mcp_client","name":"dolphin-mcp","description":"Dolphin MCP is a Python library and CLI tool for interacting with Model Context Protocol servers using natural language. It supports multiple LLMs and provides a conversational interface for accessing","category":"AI","language":"Python","stars":532,"forks":29,"owner":"cognitivecomputations","github_url":"https://github.com/cognitivecomputations/dolphin-mcp","homepage":null,"setup":"## Setup\n\nBefore installing Dolphin MCP, ensure you have the following prerequisites installed:\n\n1. **Python 3.8+**\n2. **SQLite** - A lightweight database used by the demo\n3. **uv/uvx** - A fast Python package installer and resolver\n\n### Setting up Prerequisites\n\n#### Windows\n\n1. **Python 3.8+**:\n   - Download and install from [python.org](https://www.python.org/downloads/windows/)\n   - Ensure you check \"Add Python to PATH\" during installation\n2. **SQLite**:\n   - Download the precompiled binaries from [SQLite website](https://www.sqlite.org/download.html)\n   - Choose the \"Precompiled Binaries for Windows\" section and download the sqlite-tools zip file\n   - Extract the files to a folder (e.g., `C:\\sqlite`)\n   - Add this folder to your PATH:\n     - Open Control Panel > System > Advanced System Settings > Environment Variables\n     - Edit the PATH variable and add the path to your SQLite folder\n     - Verify installation by opening Command Prompt and typing `sqlite3 --version`\n3. **uv/uvx**:\n   - Open PowerShell as Administrator and run:\n     ```\n     powershell -ExecutionPolicy ByPass -c \"irm https://astral.sh/uv/install.ps1 | iex\"\n     ```\n   - Restart your terminal and verify installation with `uv --version`\n\n#### macOS\n\n1. **Python 3.8+**:\n   - Install using Homebrew:\n     ```\n     brew install python\n     ```\n2. **SQLite**:\n   - SQLite comes pre-installed on macOS, but you can update it using Homebrew:\n     ```\n     brew install sqlite\n     ```\n   - Verify installation with `sqlite3 --version`\n3. **uv/uvx**:\n   - Install using Homebrew:\n     ```\n     brew install uv\n     ```\n   - Or use the official installer:\n     ```\n     curl -LsSf https://astral.sh/uv/install.sh | sh\n     ```\n   - Verify installation with `uv --version`\n\n#### Linux (Ubuntu/Debian)\n\n1. **Python 3.8+**:\n   ```\n   sudo apt update\n   sudo apt install python3 python3-pip\n   ```\n2. **SQLite**:\n   ```\n   sudo apt update\n   sudo apt install sqlite3\n   ```\n   - Verify installation with `sqlite3 --version`\n3. **uv/uvx**:\n   ```\n   curl -LsSf https://astral.sh/uv/install.sh | sh\n   ```\n   - Verify installation with `uv --version`\n\n## Installation\n\n### Option 1: Install from PyPI (Recommended)\n\n```bash\npip install dolphin-mcp\n```\n\nThis will install both the library and the `dolphin-mcp-cli` command-line tool.\n\n### Option 2: Install from Source\n\n1. Clone this repository:\n   ```bash\n   git clone https://github.com/cognitivecomputations/dolphin-mcp.git\n   cd dolphin-mcp\n   ```\n2. Install the package in development mode:\n   ```bash\n   pip install -e .\n   ```\n3. Set up your environment variables by copying the example file and adding your OpenAI API key:\n   ```bash\n   cp .env.example .env\n   ```\n   Then edit the `.env` file to add your OpenAI API key.\n4. (Optional) Set up the demo dolphin database:\n   ```bash\n   python setup_db.py\n   ```\n   This creates a sample SQLite database with dolphin information that you can use to test the system.","tools":"## Available Tools\n\n1.  **Multiple Provider Support** (Works with OpenAI, Anthropic, Ollama, and LMStudio models)\n2.  **Modular Architecture** (Clean separation of concerns with provider-specific modules)\n3.  **Dual Interface** (Use as a Python library or command-line tool)\n4.  **MCP Server Integration** (Connect to any number of MCP servers simultaneously)\n5.  **Tool Discovery** (Automatically discover and use tools provided by MCP servers)\n6.  **Flexible Configuration** (Configure models and servers through JSON configuration)\n7.  **Environment Variable Support** (Securely store API keys in environment variables)\n8.  **Comprehensive Documentation** (Detailed usage examples and API documentation)\n9.  **Installable Package** (Easy installation via pip with `dolphin-mcp-cli` command)","faq":null,"created_at":"2025-03-11T17:13:44+00:00","updated_at":"2025-03-28T20:22:54+00:00","source_url":"https://model-context-protocol.com/clients/python-llm-model-context-protocol-tool","related_articles":[]}