Tavily Web Search MCP Server
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., "@Tavily Web Search MCP Server find recent developments in quantum computing"
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.
AI Makerspace: MCP Session Repo for Session 13
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
Project Overview
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.
Prerequisites
Python 3.13 or higher
A valid Tavily API key
⚠️NOTE FOR WINDOWS:⚠️
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.uvwinget 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!
Installation
Clone the repository:
git clone <repository-url> cd <repository-directory>Configure environment variables: Copy the
.env.sampleto.envand 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!
Running the MCP Server
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.
Usage
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.
Activities:
There are a few activities for this assignment!
🏗️ Activity #1:
Choose an API that you enjoy using - and build an MCP server for it!
🏗️ Activity #2:
Build a simple LangGraph application that interacts with your MCP Server.
You can find details here!
Available Tools
5 toolsread_clipboardA
Read and return the current clipboard text (macOS). Uses pbpaste.
Inputs: no named parameters. Returns: result
roll_diceC
Roll the dice with the given notation
Inputs: notation (required), num_rolls. Returns: result
send_gmailC
Send an email using Gmail API. Requires GMAIL_USER and GMAIL_APP_PASSWORD environment variables.
Inputs: to (required), subject (required), body (required). Returns: result
web_searchC
Search the web for information about the given query
Inputs: query (required). Returns: result
write_clipboardA
Write the given text to the clipboard (macOS). Uses pbcopy.
Inputs: text (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
The tools have wildly different and unrelated purposes—clipboard operations, dice rolling, email sending, and web searching—with no clear thematic connection, making the set highly ambiguous as a cohesive toolset. An agent would struggle to understand why these specific tools are grouped together, leading to potential misselection based on domain assumptions.
The naming follows a consistent verb_noun pattern (e.g., read_clipboard, roll_dice, send_gmail, web_search, write_clipboard), which is predictable and readable. There are minor deviations like 'web_search' using a noun_verb structure instead, but overall the consistency is strong.
With only 5 tools, the count is reasonable in isolation, but it is inappropriate for the server's stated purpose as 'Tavily Web Search MCP Server'—only one tool (web_search) directly relates to web searching, while the others are unrelated utilities, creating a mismatch in scope.
For a web search server, there are significant gaps in coverage, such as missing tools for advanced search features, result filtering, or API configuration. The inclusion of unrelated tools like clipboard and email operations further dilutes the domain focus, making the surface incomplete for the stated purpose.
Related MCP Connectors
Provides AI assistants with access to Seltz's powerful Web Search capabilities.
Web search, scraping, Google Trends and data lookups. Paid per call in USDC on Base via x402.
Enable AI assistants to perform web searches using Perplexity's Sonar Pro.
Unofficial Tavily MCP — wraps the Tavily API (tavily.com)
Related MCP Servers
- FlicenseBqualityDmaintenanceEnables web search capabilities through the Tavily API. Allows users to search the web for information using natural language queries via the MCP protocol.41-
- FlicenseCqualityDmaintenanceEnables web search capabilities through the Tavily API. Allows users to search the web for information using natural language queries through the MCP protocol.3-
- FlicenseCqualityDmaintenanceEnables web search capabilities through the Tavily API, allowing users to perform web searches and retrieve information from the internet through natural language queries.3-
- FlicenseCqualityDmaintenanceEnables web search capabilities through the Tavily API, allowing users to search the web for information using natural language queries through the Model Context Protocol.21-