mcpField
D
Demo MCP

Demo MCP

Local
github.com/josxDeveloper Tools2Updated 79w ago
Repository

About Demo MCP

Demo MCP is a Python example project containing an MCP server, client, and host integrations. It is intended for exploring server setup, SSE client connections, and debugging with Inspector.

Key features

  1. 01Run example MCP servers
  2. 02Connect with a Python demo client
  3. 03Try a LangChain or LangGraph host
  4. 04Debug with MCP Inspector

Use cases

  1. 01Explore a basic MCP server setup
  2. 02Test an SSE client connection
  3. 03Try an MCP host with Ollama
  4. 04Inspect and debug a server

MCP support

Includes example MCP servers and a Python client that connects to an SSE endpoint. MCP Inspector is used to connect to and test the server.

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

Demo MCP

Info

Setup

python3 -m venv .venv
. .venv/bin/activate
pip install -r requirements.txt

Run Server

You can use any of this two servers

  • python server.py or with jwt auth python server_asgi.py

Run demo client

  • python client.py http://localhost:8000/sse

Run demo host (langchain/langgraph)

You need to run ollama and download a model

  • python host_langchain.py llama3.3 http://localhost:11434

Debug

You can debug server with this app

  • Open a new terminal and run npx @modelcontextprotocol/inspector
  • Point browser to http://127.0.0.1:6274
  • Change Transport Type to SSE
  • Change URL to http://localhost:8000/sse
  • Press Connect and start testing server

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.