dolphin-mcp  by QuixiAI

CLI tool/Python library for interacting with Model Context Protocol (MCP) servers

created 4 months ago
501 stars

Top 62.9% on sourcepulse

GitHubView on GitHub
Project Summary

Dolphin MCP is a Python library and CLI tool for interacting with Model Context Protocol (MCP) servers, enabling natural language queries to any LLM-backed tool. It's designed for developers and researchers who need to integrate LLMs with external data sources and services via the MCP standard.

How It Works

The library connects to multiple MCP servers, discovers their exposed tools, and makes them available to LLMs from providers like OpenAI, Anthropic, Ollama, and LMStudio. It uses a function-calling mechanism to route user queries through the LLM, which then selects and calls the appropriate tools. The results are processed and returned conversationally. This modular approach allows for easy extension to new LLM providers and MCP servers.

Quick Start & Requirements

  • Install: pip install dolphin-mcp-cli
  • Prerequisites: Python 3.8+, SQLite, uv/uvx. Installation instructions are provided for Windows, macOS, and Linux.
  • Configuration: Requires .env for API keys and mcp_config.json to define MCP servers.
  • Demo: Optional SQLite database setup with python setup_db.py.
  • Docs: Comprehensive usage examples and API documentation are available.

Highlighted Details

  • Supports multiple LLM providers: OpenAI, Anthropic, Ollama, LMStudio.
  • Connects to any number of MCP servers simultaneously.
  • Automatically discovers and utilizes tools exposed by MCP servers.
  • Offers both a Python library API (run_interaction) and a CLI tool (dolphin-mcp-cli).

Maintenance & Community

  • Contributions are welcome via Pull Requests.
  • No specific community links (Discord/Slack) or roadmap are mentioned in the README.

Licensing & Compatibility

  • License information is explicitly missing from the README.
  • Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The README does not specify the project's license, which is a critical factor for adoption, especially in commercial or closed-source environments. There is also no mention of community support channels or a roadmap for future development.

Health Check
Last commit

2 months ago

Responsiveness

1 day

Pull Requests (30d)
1
Issues (30d)
0
Star History
130 stars in the last 90 days

Explore Similar Projects

Starred by Didier Lopes Didier Lopes(Founder of OpenBB), Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems), and
2 more.

fastmcp by jlowin

2.1%
15k
Pythonic SDK for building Model Context Protocol (MCP) servers/clients
created 8 months ago
updated 1 day ago
Feedback? Help us improve.