mcpField
M
mcp-test

mcp-test

Local
github.com/kavinduhapuDeveloper Tools0Updated 52w ago
Repository

About mcp-test

mcp-test is a set of tutorials for integrating MCP servers with LLM apps, using LangChain's MCP adapters. It includes a weather server example, client run instructions, and steps for listing tools with MCP Inspector.

Key features

  1. 01Demonstrate MCP server integration with LLM apps
  2. 02Use LangChain MCP adapters
  3. 03Include a weather server example
  4. 04Inspect tools with MCP Inspector

Use cases

  1. 01Learn to run an MCP weather server
  2. 02Test MCP client integration
  3. 03View available tools in Inspector

MCP support

The tutorials use an MCP server and client, and show how to list the weather server's tools with MCP Inspector.

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

mcp-test

Tutorials on mcp server integration with LLM apps. Using https://github.com/langchain-ai/langchain-mcp-adapters

To setup & run

  • Create venv and install dependencies on requirements.txt
  • Create .env file with relavant with API keys for example GOOGLE_API_KEY
  • Start weather mcp server by
python3 weather_server.py
  • Run client using
python3 multiple_client.py

To list the tools using MCP inspector

  • Make sure NodeJs and npm are installed https://nodejs.org/en/download
  • Install MCP cli using pip pip install mcp-cli
  • Run the server using python weather_server.py
  • In another terminal run mcp inspector using mcp dev weather_server.py
  • This will open up web UI in your browser.
  • Go to tools section and click on list tools alt text

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.