Tiny Chat
@to-aoki
About Tiny Chat
This is an LLM application with chat functionality, featuring chat using RAG, a database, and MCP server capabilities. The UI is designed for Japanese users.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"tiny_chat": {
"command": "python",
"args": [
"-m",
"build"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Tiny Chat?
Tiny Chat is a chat application with an MCP (Model Context Protocol) server, a web interface, and an OpenAI-compatible RAG API. It integrates with Qdrant for retrieval-augmented generation and supports local databases. It is intended for developers and Claude Desktop users who need a self-hosted chat system with retrieval capabilities.
How to use Tiny Chat?
Install the package via pip, then run the web interface using tiny-chat (or streamlit run tiny_chat/main.py for development). Configure the MCP server in Claude Desktop by specifying the path to the tiny-chat-mcp binary and a DB_CONFIG environment variable. Alternatively, start the OpenAI Chat API RAG server with tiny-chat-api and query it using the model name set to a Qdrant collection name.
Key features of Tiny Chat
- Web interface built with Streamlit
- MCP server integration for Claude Desktop
- OpenAI-compatible Chat Completions API
- RAG (Retrieval-Augmented Generation) using Qdrant
- Local database support (with DB_CONFIG)
Use cases of Tiny Chat
- Provide a local chat interface with RAG knowledge retrieval
- Connect Claude Desktop to a custom Qdrant-backed knowledge base
- Serve as an OpenAI-compatible backend for custom frontend applications
- Run a minimal chat system with or without a database
FAQ from Tiny Chat
What Python version is required?
Tiny Chat is tested with Python 3.10 or later.
How do I set up the MCP server for Claude Desktop?
Add a JSON entry to your Claude Desktop configuration with the command pointing to the tiny-chat-mcp binary and the environment variable DB_CONFIG set to the database configuration file path.
What does the model parameter do in the API?
The model parameter in the Chat Completions request specifies the target Qdrant collection name. Changing the model changes which collection is searched.
Can I run Tiny Chat without a database?
Yes. Use the --database flag to enable database mode; omitting it runs the application without a database backend.
What transport does the MCP server use?
The MCP server is launched as a subprocess (command) by Claude Desktop; the README does not specify the transport protocol.
Frequently asked questions
What Python version is required?
Tiny Chat is tested with Python 3.10 or later.
How do I set up the MCP server for Claude Desktop?
Add a JSON entry to your Claude Desktop configuration with the command pointing to the `tiny-chat-mcp` binary and the environment variable `DB_CONFIG` set to the database configuration file path.
What does the `model` parameter do in the API?
The `model` parameter in the Chat Completions request specifies the target Qdrant collection name. Changing the model changes which collection is searched.
Can I run Tiny Chat without a database?
Yes. Use the `--database` flag to enable database mode; omitting it runs the application without a database backend.
What transport does the MCP server use?
The MCP server is launched as a subprocess (command) by Claude Desktop; the README does not specify the transport protocol.
Basic information
More AI & Agents MCP servers
Model Context Protocol Server for Home Assistant
tevonsbA MCP server for Home Assistant
🛡️ A.I.G(AI-Infra-Guard)
TencentA full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
XDC AI
XDC AI is a remote MCP server available at https://xdcai.tech.
1Panel
1Panel-dev🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.
Mcp Agent
lastmile-aiBuild effective agents using Model Context Protocol and simple workflow patterns
Comments