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/AIE8-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
4 toolsload_bookmark_dataB
Load bookmarks and history data from files
Inputs: data_folder. Returns: result
organize_and_categorizeB
Clean, deduplicate, and categorize bookmark data
Inputs: data_folder, output_folder. Returns: result
roll_diceC
Roll the dice with the given notation
Inputs: notation (required), num_rolls. Returns: result
web_searchC
Search the web for information about the given query
Inputs: query (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 4 tools
The tools have unclear boundaries and overlapping purposes. 'load_bookmark_data' and 'organize_and_categorize' both deal with bookmark data, making it ambiguous which to use for basic operations. 'roll_dice' is completely unrelated to the web search/domain theme, creating confusion about the server's core purpose. An agent would struggle to differentiate when to use each tool appropriately.
The naming conventions are mixed but still readable. 'load_bookmark_data' and 'web_search' follow a verb_noun pattern, while 'organize_and_categorize' uses a verb_and_verb style and 'roll_dice' is a simple verb_noun. There's no consistent pattern across all tools, but the names are descriptive enough to understand their functions individually.
With only 4 tools, the count feels too thin for a 'Tavily Web Search MCP Server' as implied by the name. The inclusion of unrelated tools like 'roll_dice' and bookmark management functions suggests poor scoping. A focused web search server would typically have more search-related operations, making this set appear incomplete and mismatched to its stated purpose.
There are significant gaps in the tool surface for a web search domain. While 'web_search' exists, there's no support for advanced search features, result filtering, or search history management. The bookmark tools are incomplete without create/update/delete operations, and 'roll_dice' is entirely out of scope. This creates dead ends for agents trying to perform comprehensive web search tasks.
Maintenance
Related MCP Connectors
Unofficial Tavily MCP — wraps the Tavily API (tavily.com)
Web search API and MCP server for developers building AI agents.
Web search and clean-text fetch MCP server (Tavily-powered, SSRF-guarded).
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
Related MCP Servers
- FlicenseCqualityDmaintenanceEnables web search capabilities through the Tavily API, allowing users to search the internet for information using natural language queries. Demonstrates MCP server implementation with external API integration.3-
- FlicenseNot gradedqualityDmaintenanceEnables web search capabilities through the Tavily API, allowing users to search the web for information using natural language queries. Demonstrates MCP server implementation with stdio transport mode for integration with LLM applications.-
- FlicenseAqualityDmaintenanceEnables web search capabilities through the Tavily API and serves as a demonstration platform for building custom MCP tools. Designed for educational purposes to showcase MCP server development and LangGraph integration.6-
- FlicenseCqualityDmaintenanceEnables web search capabilities through the Tavily API, allowing users to search the internet for information using natural language queries. Built as a demonstration MCP server running in stdio transport mode.3-