mcp_chatbot and mcp-playground
About mcp_chatbot
keli-wen/mcp_chatbot
A chatbot implementation compatible with MCP (terminal / streamlit supported)
Integrates custom MCP servers (like markdown processing tools) with LLMs via stdio transport, enabling multi-turn tool-use workflows with response parsing for sequential and parallel MCP calls. Provides three UI options—CLI, interactive terminal, and Streamlit—with both streaming and regular response modes, supporting flexible LLM backends including OpenAI-compatible APIs and Ollama.
About mcp-playground
Elkhn/mcp-playground
A Streamlit-based chat app for LLMs with plug-and-play tool support via Model Context Protocol (MCP), powered by LangChain, LangGraph, and Docker.
Supports dynamic MCP server registration and multi-provider LLM switching (OpenAI, Bedrock, Anthropic, Google, Groq) through a single LangChain interface, with a ReAct agent via LangGraph that auto-detects and routes tool calls. Containerized with Docker Compose and uses uv for fast dependency resolution, allowing extensible drop-in MCP servers and custom model overrides directly from the Streamlit UI without configuration file edits.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work