mcp-intro
Click on "Deploy 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., "@mcp-introAdd 12 and 34 for me"
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.
mcp-intro
A minimal Model Context Protocol server built
with the official Python SDK (mcp 2.x). It exposes two tools, one resource, and
one prompt so you can see each MCP primitive working end to end.
Contents
Path | Description |
| The MCP server. Defines the |
| A pure-Python client that spawns |
| Python dependencies — just |
| Ignores the virtualenv and Python bytecode. |
| Local virtual environment (not committed). |
Related MCP server: MCP Server Basic Example
What the server provides
Tools
add(a: int, b: int) -> int— returnsa + b.greet(name: str) -> str— returns"Hello, {name}!".
Resource
config://version— returns the server version string ("1.0.0").
Prompt
summarize(text: str)— a reusable prompt template that asks the model to summarizetextin one sentence.
Setup
Requires Python 3.13+ (the checked-in .venv uses 3.13).
cd /Users/amoghmadireddi/pl/mcp-intro
# Create the virtualenv if it does not already exist
python3 -m venv .venv
# Install dependencies
./.venv/bin/python -m pip install -r requirements.txtRunning the server
The server speaks the stdio transport, so it is normally launched by an MCP client rather than run by hand. To start it directly:
./.venv/bin/python server.pyIt will sit waiting for MCP protocol messages on stdin/stdout — this is expected.
Press Ctrl+C to stop.
Quick smoke test (pure Python)
./.venv/bin/python client_demo.pyExpected output:
tools: ['add', 'greet']
add(2, 3) -> 5
greet('Ada') -> Hello, Ada!
resources: ['config://version']
config://version -> 1.0.0
prompts: ['summarize']
summarize(...) -> Summarize the following text in one sentence:
MCP is a protocol.Using it interactively (MCP Inspector)
The mcp CLI (installed via mcp[cli]) can launch the server with a web-based
inspector for poking at tools, resources, and prompts:
./.venv/bin/mcp dev server.pyRequires Node.js — mcp dev shells out to npx to run the MCP Inspector.
On macOS: brew install node.
Then open the URL it prints (it includes an auth token and usually opens your browser automatically). Click Connect, then from the inspector you can:
call
addwith e.g.a = 2,b = 3and see5call
greetwithname = "Ada"and seeHello, Ada!read the
config://versionresourcerender the
summarizeprompt with some text
Using it from an MCP client
Register the server with any MCP-capable client (Claude Desktop, Claude Code,
etc.) by pointing it at the virtualenv's Python and server.py.
Example client config entry:
{
"mcpServers": {
"mcp-intro": {
"command": "/Users/amoghmadireddi/pl/mcp-intro/.venv/bin/python",
"args": ["/Users/amoghmadireddi/pl/mcp-intro/server.py"]
}
}
}For Claude Code specifically:
claude mcp add mcp-intro -- /Users/amoghmadireddi/pl/mcp-intro/.venv/bin/python /Users/amoghmadireddi/pl/mcp-intro/server.pyOnce connected, the client can list and call the add / greet tools, read the
config://version resource, and use the summarize prompt.
Extending it
Add a new tool by writing a function and decorating it:
@mcp.tool()
def multiply(a: int, b: int) -> int:
"""Multiply two numbers."""
return a * bThe type hints define the input schema and the docstring becomes the tool description shown to clients.
This server cannot be deployed
Maintenance
Related MCP Connectors
Generate contextual prompts and reusable agent skills, evaluate prompts with the 16-dimension Prompt Score, and manage saved work in PromptDrive. Twelve MCP tools also provide authorized access to private Memory for source-grounded answers. Connect over Streamable HTTP using OAuth 2.1 and PKCE. Generation consumes account quota and automatically saves successful results; Memory access follows account permissions and plan limits.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
OpenAI-compatible LLM MCP (7 tools); chat via balance key or x402 USDC on Base
Related MCP Servers
- AlicenseNot gradedqualityNot gradedmaintenanceA demonstration MCP server that provides calculator tools for arithmetic operations, personalized greeting resources, and code review prompt templates. Enables users to perform basic math calculations, generate dynamic greetings, and access reusable code review templates through the Model Context Protocol.MIT
- AlicenseNot gradedqualityDmaintenanceA foundational Model Context Protocol server demonstrating core functionality through basic arithmetic tools and personalized greeting resources. It serves as a template for developers learning to build and deploy MCP-enabled AI applications.GPL 3.0
- FlicenseNot gradedqualityDmaintenanceDemonstrates core MCP server functionality with basic arithmetic operations (addition and subtraction) and personalized greeting generation. Serves as an educational template implementing example tools and dynamic resources for MCP server development with Python.-
- FlicenseNot gradedqualityDmaintenanceA simple MCP server demonstrating resources, tools, and prompts, including a greeting resource, an addition tool, and a calculation prompt.-