mcpField
T
Tiny Chat

Tiny Chat

Local
github.com/to-aokiAI & Agents2Updated 45w ago
Repository

About Tiny Chat

Tiny Chat is an LLM chat application with RAG and a database, with a web interface designed for Japanese users. It also provides an MCP server and an OpenAI Chat API-compatible RAG server.

Key features

  1. 01RAG chat
  2. 02Database-only mode
  3. 03Streamlit web interface
  4. 04OpenAI Chat API RAG server

Use cases

  1. 01Retrieving database content through chat
  2. 02Running the database-only mode
  3. 03Searching a Qdrant collection through the Chat API

MCP support

Tiny Chat can run as an MCP server. The README shows an example configuration for connecting it to Claude Desktop using its command and database configuration file.

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

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Tiny Chat

Ask DeepWiki

Installation

Tested with Python 3.10 or later

Development Installation
pip install -r requirements.txt
Package Installation
# Build the package
pip install build
python -m build

# Install the built package
pip install dist/*.whl

Web Interface Usage

Running from source (development)
streamlit run tiny_chat/main.py --server.address=127.0.0.1
only database (development)
streamlit run tiny_chat/main.py --server.address=127.0.0.1 -- --database
Running installed package
tiny-chat
only database
tiny-chat --database

img.png

MCP Usage

Claude Desktop example.

{
  "mcpServers": {
    "tiny-chat": {
      "command": "/path/to/tiny_chat/.venv/bin/tiny-chat-mcp",
      "env": {
        "DB_CONFIG": "/path/to/tiny_chat/database_config.json"
      }
    }
  }
}

OpenAI Chat API RAG Server Usage

tiny-chat-api

model: target search qdrant collection name (model change in conversation).

curl http://localhost:8080/v1/chat/completions   -H "Content-Type: application/json"   -d '{"model": "qdrant-collection-name", "messages": [{"role": "user", "content": "カレーライスの材料は？"}]}'

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.