mcp-chatbot

What is mcp-chatbot?

mcp-chatbot is a modular, async research assistant that combines Anthropic Claude 3 with the Model Context Protocol (MCP), delivering on‑demand literature search and summarization for academics and engineers. It runs as a CLI tool, deployable via Docker or directly on Python.

How to use mcp-chatbot?

Clone the repository, install dependencies with pip install -e . (or uv pip install -e .[dev] for dev), then start the research server with python research_server.py and launch the chatbot CLI with mcp-chatbot run. Alternatively, build and run with Docker using docker build -t mcp-chatbot:0.1 . then docker run --rm -it -p 8001:8001 -p 8000:8000 mcp-chatbot:0.1.

Key features of mcp-chatbot

• Combines Anthropic Claude 3 with MCP for tool‑augmented queries
• REPL mode for interactive, free‑form research conversations
• One‑shot query mode for quick, single‑question answers
• Modular architecture with a separate research MCP server
• Asynchronous design for efficient literature search
• Caches paper metadata locally by topic

Use cases of mcp-chatbot

• Academic researchers quickly finding and summarizing papers on a given topic
• Engineers exploring the latest trends in AI subfields like diffusion models
• Literature review automation by chaining multiple queries with tool invocations
• Ad‑hoc Q&A about stored papers using the /prompts and @folders commands
• Prototyping MCP‑integrated agents in a CLI environment

FAQ from mcp-chatbot

What does mcp-chatbot do that other chatbots don’t?

It combines Anthropic Claude 3 with the Model Context Protocol to let Claude autonomously invoke research‑specific tools (search_papers, extract_info) during conversation, making it a specialized research assistant rather than a general‑purpose chatbot.

Which models and platforms does it support?

It uses Anthropic Claude 3 (default model configurable via ANTHROPIC_MODEL environment variable). It runs on Linux, macOS, and Windows (Git Bash or WSL recommended; standard Command Prompt/PowerShell may not work with uv).

What MCP servers does it support?

It includes a built‑in research MCP server with search_papers and extract_info tools. Known issues exist connecting to external fetch and filesystem MCP servers (reported as “Method not found”).

What is the pricing/licensing for mcp-chatbot?

It is open source under the MIT License (Copyright © 2025). Using Anthropic Claude 3 requires an API key and incurs usage costs from Anthropic.

Are there any known limitations?

Yes. When running mcp-chatbot run, the tool may fail to connect to 'fetch' and 'filesystem' MCP servers due to “Method not found” errors. The roadmap mentions future additions like vector search and a web UI.