mcp_chatbot and mcp-chatbot
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-chatbot
mctrinh/mcp-chatbot
MCP Chatbot powered by Anthropic Claude. Delivering on‐demand literature search and summarisation for academics and engineers
Implements an async research assistant that routes Claude 3 queries through the Model Context Protocol (MCP) to dynamically invoke `search_papers` and `extract_info` tools, with a Typer-based CLI offering both interactive REPL and one-shot query modes. The architecture separates concerns into a standalone MCP research server (handling literature retrieval) and a chatbot engine that determines tool invocation based on query intent, with configuration via environment variables and JSON. Designed for local deployment via Docker or direct Python execution with `uv` package management, supporting cached paper metadata organization by research topic.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work