mcp-chatbot
- other
MCP Chatbot powered by Anthropic Claude. Delivering on‐demand literature search and summarisation for academics and engineers
About
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.
Details
- Author
- mctrinh
- GitHub stars
- 9
- Category
- other
- Repository
- mctrinh/mcp-chatbot
mcp-chatbot
A modular, async research assistant that combines Anthropic Claude 3 with the Model Context Protocol (MCP), delivering on‐demand literature search and summarisation for academics and engineers.
---
1. Project Structure
mcp-chatbot/
├── Dockerfile
├── pyproject.toml
├── uv.lock
├── README.md
├── server_config.json
├── research_server.py
├── papers/ # Cached paper metadata by topic
├── mcp_chatbot/
│ ├── __init__.py
│ ├── cli.py # Typer-based CLI
│ └── core.py # Main chatbot engine
└── tests/
└── test_core.py
2. Quick Start
2.1. Clone the Repository
git clone https://github.com/mctrinh/mcp-chatbot.git
cd mcp-chatbot
2.2. Install Dependencies
Install uv (recommended)
# Git Bash or WSL on Windows, doesn't work in standard Command Prompt or PowerShell
curl -LsSf https://astral.sh/uv/install.sh | sh
Scoop (Windows)
scoop install uv
Chocolatey (Windows - Administrator Command Prompt - Recommended)
choco install uv
uv --version
Install Python packages in project.dependencies in pyproject.toml
pip install -e .
3. Build and Run with Docker
# Build image
docker build -t mcp-chatbot:0.1 .
Run server and CLI (ports 8001 and 8000)
docker run --rm -it -p 8001:8001 -p 8000:8000 mcp-chatbot:0.1
4. Run Without Docker (Local Dev)
# Install dependencies
uv pip install -e .[dev]
Start the research server (MCP tool)
python research_server.py
In a new terminal, launch the chatbot CLI
mcp-chatbot run
5. Try the Chatbot
5.1. REPL Mode
python -m mcp_chatbot.cli run
mcp-chatbot run
/prompts # list Claude prompts
@folders # list downloaded paper topics
AI alignment # ask anything – Claude decide whether to invoke tools
5.2. One-shot Query
mcp-chatbot once "What are the latest trends in diffusion models?"
6. Configuration (Optional)
Environment variables andserver_config.json control model and ports:
export ANTHROPIC_MODEL="claude-3-opus-20240229"
export RESEARCH_PORT=8001
export PAPER_DIR=./papers
7. Testing
# Installs pytest, coverage, etc.
uv pip install -e .[dev]
Run unit tests
pytest -q
With coverage (optional)
pytest --cov=mcp_chatbot
8. Road map
- Research MCP server withsearch_papers and extract_info (done)
- Tool usage via Claude 3 (done)
- Prompt orchestration (done)
- Vector search over stored papers (Faiss / Chroma)
- Web UI using FastAPI + React
- GitHub Actions for CI/CD
9. License
MIT License. Copyright © 2025.10. Current Issues
Issues occur when running ``mcp-chatbot run``
- <span style="color:red;">⚠ Could not connect to server 'fetch': Method not found</span>
- <span style="color:red;">⚠ Could not connect to server 'filesystem': Method not found</span>
