Tiny Chat
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Tiny ChatSearch the knowledge base for information on API rate limits"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Tiny Chat
Installation
Tested with Python 3.10 or later
Development Installation
pip install -r requirements.txtPackage Installation
# Build the package
pip install build
python -m build
# Install the built package
pip install dist/*.whlWeb Interface Usage
Running from source (development)
streamlit run tiny_chat/main.py --server.address=127.0.0.1only database (development)
streamlit run tiny_chat/main.py --server.address=127.0.0.1 -- --databaseRunning installed package
tiny-chatonly database
tiny-chat --database
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-apimodel: 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?"}]}'This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/to-aoki/tiny_chat'
If you have feedback or need assistance with the MCP directory API, please join our Discord server