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-server search for latest developments in AI"
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.
This project is a demonstration of the MCP (Model Context Protocol) server, which utilizes the Tavily API for web search capabilities. The server is designed to run in a standard input/output (stdio) transport mode.
Related MCP server: Tavily Web Search MCP Server
The MCP server is set up to handle web search queries using the Tavily API. It is built with the following key components:
TavilyClient: A client for interacting with the Tavily API to perform web searches.
Python 3.13 or higher
A valid Tavily API key
You'll need to install this on the Windows side of your OS.
This will require getting two CLI tool for Powershell, which you can do as follows:
winget install astral-sh.uv
winget install --id Git.Git -e --source winget
After you have those CLI tools, please open Cursor into Windows.
Then, you can clone the repository using the following command in your Cursor terminal:
git clone https://AI-Maker-Space/AIE7-MCP-Session.gitAfter that, you can follow from Step 2. below!
Clone the repository:
git clone <repository-url>
cd <repository-directory>Configure environment variables:
Copy the .env.sample to .env and add your Tavily API key:
TAVILY_API_KEY=your_api_key_here🏗️ Add a new tool to your MCP Server 🏗️
Create a new tool in the server.py file, that's it!
To start the MCP server, you will need to add the following to your MCP Profile in Cursor:
NOTE: To get to your MCP config. you can use the Command Pallete (CMD/CTRL+SHIFT+P) and select "View: Open MCP Settings" and replace the contents with the JSON blob below.
{
"mcpServers": {
"mcp-server": {
"command" : "uv",
"args" : ["--directory", "/PATH/TO/REPOSITORY", "run", "server.py"]
}
}
}The server will start and listen for commands via standard input/output.
The server provides a web_search tool that can be used to search the web for information about a given query. This is achieved by calling the web_search function with the desired query string.
There are a few activities for this assignment!
Choose an API that you enjoy using - and build an MCP server for it!
Build a simple LangGraph application that interacts with your MCP Server.
You can find details here!
Roll the dice with the given notation
Inputs: notation (required), num_rolls. Returns: result
Get consolidated stock information about a stock TICKER
Inputs: ticker (required). Returns: result
Search the web for information about the given query
Inputs: query (required). Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool targets a completely different domain: dice rolling, stock info, and web search. There is no overlap or ambiguity between them.
All names use snake_case, but 'roll_dice' follows a verb_noun pattern while 'stock_info' and 'web_search' are noun_noun. This is a minor inconsistency but still readable.
With 3 tools, the set is small but still feels reasonable for a general-purpose utility server. It is not excessively thin for the apparent scope.
The tools cover three unrelated functionalities with no common domain. There is no coverage of typical CRUD or lifecycle operations, and the set seems arbitrarily assembled without a clear purpose.
Web search API and MCP server for developers building AI agents.
Web search and clean-text fetch MCP server (Tavily-powered, SSRF-guarded).
MCP server for Google search results via SERP API