Integrates with Google Gemini API to translate natural language user queries into structured tool calls. The LLM analyzes user intent and generates appropriate function calls to tools exposed by the MCP server.
Leverages Pydantic models to define input/output schemas for tools, enabling automatic validation of tool parameters and return values.
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., "@Model Context Protocol Demo calculate the average of 15, 25, and 35"
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.
Related MCP server: MCP Demo Server
A high-level, fast, Pythonic way to build MCP servers and clients
# install
pip install fastmcp
# verify version
fastmcp version
FastMCP version: 2.5.2
MCP version: 1.9.2
Python version: 3.13.2
Platform: Linux-6.8.0-60-generic-x86_64-with-glibc2.35
FastMCP root path: ~/anaconda3/envs/mcp/lib/python3.13/site-packages
# dev install
git clone https://github.com/jlowin/fastmcp.git
cd fastmcp
uv sync
A framework with complete, end-to-end tested MCP Feature support including Sampling, which helps create and interact with sophisticated Agents and Workflows in minutes. Both Anthropic (Haiku, Sonnet, Opus) and OpenAI models (gpt-4o/gpt-4.1 family, o1/o3 family) are supported
A fastmcp tutorial
MCP server:
mcp_server.py: collection of tools/resources like calculator, trigonometry function, yahoo finance API call
MCP clients:
mcp_client_simple.py: simple client with rule-based query parsing
mcp_client_llm.py: client with LLM-based query parsing
mcp_client_llm_resource.py: client with LLM parsing and calling tool/resource (see readme_tool_resource.md for details)
see readme_gemini.md for more details
conda create -n mcp
conda activate mcp
git clone https://github.com/digital-duck/mcp_demo.git
cd mcp_demo/fastmcp
pip install -r requirements.txt
# in 1st terminal
python mcp_server.py
# in 2nd terminal
python mcp_client_llm_resource.py
# python mcp_client_simple.py
# python mcp_client_llm.pysee fastmcp/README.md
streamlit run st_mcp_rag.pyTo Be Built
see readme_aws.md for more details
see mcp_sdk sub-folder
To Be Verified
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
MCP server exposing the Backtest360 engine API as tools for AI agents.
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/digital-duck/mcp_demo'
If you have feedback or need assistance with the MCP directory API, please join our Discord server