Skip to main content
Glama
Simple MCP Server

Simple MCP Server

๐Ÿงฎ Simple MCP Server (built with FastMCP)

Python FastMCP MCP

A "Hello World" MCP (Model Context Protocol) server built with FastMCP โ€” a small calculator server you can talk to over in-memory, HTTP, and STDIO transports, plus a LangGraph ReAct agent that uses its tools.

It exposes:

Type

Name

Description

๐Ÿ› ๏ธ Tool

add(a, b)

Add two integers

๐Ÿ› ๏ธ Tool

subtract(a, b)

Subtract b from a

๐Ÿ“„ Resource

file:///endpoint/{name}

Returns a template message

๐Ÿ“„ Resource

file://endpoint2/{name}

Reads a real file from ./path/

๐Ÿ’ฌ Prompt

review_code(code)

A reusable "review this code" template


Project structure

simple-MCP-server-built-with-FastMCP/
โ”œโ”€โ”€ server.py            # the FastMCP server (tools + resources + prompt)
โ”œโ”€โ”€ client_inmemory.py   # test in the same process (no network)
โ”œโ”€โ”€ client_http.py       # connect over HTTP
โ”œโ”€โ”€ client_stdio.py      # spawn the server as a subprocess (STDIO)
โ”œโ”€โ”€ agent_example.py     # LangGraph ReAct agent that uses the tools
โ”œโ”€โ”€ path/                # files served by the file resource
โ”‚   โ”œโ”€โ”€ README.txt
โ”‚   โ””โ”€โ”€ examples.txt
โ”œโ”€โ”€ requirements.txt
โ”œโ”€โ”€ .env.example         # API key template (for the agent only)
โ””โ”€โ”€ README.md

Related MCP server: MCP Calculator Demo

Setup

cd simple-MCP-server-built-with-FastMCP

python -m venv .venv
# Windows (PowerShell):
.\.venv\Scripts\Activate.ps1
# macOS / Linux:
source .venv/bin/activate

pip install -r requirements.txt

Run it

1. Quick test โ€” in-memory (no network, no API key)

python client_inmemory.py

Calls the tools, lists them, reads both resources, and renders the prompt.

2. HTTP transport

Terminal A (start the server):

python server.py http        # serves http://127.0.0.1:8000/mcp

Terminal B (run the client):

python client_http.py

3. STDIO transport

python client_stdio.py       # spawns server.py itself โ€” nothing to start first

4. ReAct agent (needs an API key)

# one-time: copy the template and add a key
Copy-Item .env.example .env   # then edit .env  (GROQ_API_KEY is free)
python agent_example.py

The agent loads the MCP tools, then answers "What is 8 + 7? Use the tools." by actually calling the add tool.

๐Ÿ’ก Groq is free โ€” get a key at console.groq.com. The agent uses Groq if GROQ_API_KEY is set, otherwise OpenAI.


How MCP transports differ

  • In-memory โ€” client and server share one Python process (simplest; for testing).

  • HTTP โ€” server runs as a web service; clients connect by URL (good for remote/shared).

  • STDIO โ€” client launches the server as a child process and talks over stdin/stdout (good for local tools).

The same tools/resources/prompt work over all three โ€” only the "wire" changes.


Credits

Based on the IBM Skills Network lab "Hello World of MCP Servers." Built with FastMCP, LangGraph, and langchain-mcp-adapters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogโ€ฆ

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      A simple MCP server that provides a calculator tool, dynamic greeting resources, and code review prompts, demonstrating how to build standardized interfaces for LLM applications.
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      A simple demonstration MCP server built with FastMCP that exposes basic calculator operations (add, subtract, multiply, divide) as tools for MCP clients like GitHub Copilot Agent mode.
      -
    • A
      license
      A
      quality
      D
      maintenance
      A minimal MCP server example demonstrating Tools, Resources, and Prompts. It enables calculations, time queries, note management, and code review prompts via stdio transport.
      3
      MIT