MCP.so
Sign In

Tiny Chat

@to-aoki

Repository

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.

#chat#continue#rag#qdrant#mcp-server#openai-like

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.

Comments

Basic information

Category

AI & Agents

License

MIT

Transports

stdio

Author

to-aoki

More AI & Agents MCP servers

Lumify Sports Intelligence

Lumify

Agent-ready sports intelligence API: live scores, odds, line movement, public betting splits, and explainable bet confidence — via 16 MCP tools at https://lumify.ai/mcp. Get a free key instantly — no signup, email, or ca

MCP Server - Remote MacOs Use

baryhuang

The only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App

487

Web Agent Protocol

OTA-Tech-AI

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

500

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416

bsv.cx

Andy Rowe

Timestamp and verify evidence on-chain. Let your agent prove what it saw and when. bsv.cx gives an AI agent verifiable memory. Timestamp a hash of any output, archive a web page as it looked, or fetch a URL with a recei