Skip to main content
Glama
MCP Server for Session 13

MCP Server for Session 13

by rach16

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: Web Search Neo

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.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/AIE8-MCP-Session.git

After that, you can follow from Step 2. below!

Installation

  1. Clone the repository:

    git clone <repository-url>
    cd <repository-directory>
  2. Configure environment variables: Create a .env file and add your API keys:

    TAVILY_API_KEY=your_tavily_api_key_here
    NEWS_API_KEY=your_news_api_key_here
  3. 🏗️ 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 several tools for different functionalities:

Available Tools:

  1. web_search(query: str) - Search the web for information about a given query using Tavily API

  2. roll_dice(notation: str, num_rolls: int) - Roll dice with custom notation (e.g., "2d6", "1d20")

  3. get_marketing_news(company: str, category: str, num_articles: int) - Get latest marketing and business news from companies like ZoomInfo, 6sense, HubSpot, etc.

  4. get_company_news(company: str, num_articles: int) - Get specific news about a particular company

Example Usage:

  • get_marketing_news() - Get general marketing tech news

  • get_marketing_news(company="ZoomInfo") - Get ZoomInfo-specific news

  • get_company_news(company="6sense") - Get 6sense company news

  • roll_dice("2d6", 3) - Roll 2 six-sided dice 3 times

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.

Files for Activity #2:

  • langgraph_app.py - LangGraph application with MCP integration

To test Activity #2:

uv run langgraph_app.py

Available Tools

4 tools
get_company_newsA

Get specific news about a particular company (e.g., ZoomInfo, 6sense, etc.)

Args: company: Company name to search for num_articles: Number of articles to return (default: 3)

Inputs: company (required), num_articles.

get_marketing_newsB

Get the latest marketing and business news from companies like ZoomInfo, 6sense, and other marketing tech companies.

Args: company: Specific company to search for (e.g., 'ZoomInfo', '6sense', 'HubSpot', 'Salesforce') category: News category (default: 'business', options: 'business', 'technology', 'general') num_articles: Number of articles to return (default: 5, max: 100)

Inputs: company, category, num_articles.

roll_diceC

Roll the dice with the given notation

Inputs: notation (required), num_rolls.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.4/5.0

    Scored across 4 tools

    Disambiguation2/5

    get_company_news and get_marketing_news have significant overlap, both retrieving news about marketing tech companies, making it unclear which to use. The other tools (roll_dice, web_search) are unrelated, further complicating disambiguation.

    Naming Consistency2/5

    Two tools follow a 'get_X_news' pattern, but roll_dice and web_search break that pattern, using different verb styles. The naming is inconsistent across the set.

    Tool Count2/5

    With only 4 tools spanning news, dice rolling, and web search, the count feels arbitrary and too small for a coherent domain. The server appears to bundle unrelated utilities.

    Completeness1/5

    The coverage is severely incomplete for any clear purpose. If focused on marketing news, dice rolling and web search are extraneous; if general, many common operations are missing. The set lacks a coherent domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      B
      quality
      D
      maintenance
      Enables web search capabilities through the Tavily API. Allows users to search the web for information using natural language queries via the MCP protocol.
      4
      1
      -
    • F
      license
      C
      quality
      D
      maintenance
      An MCP server providing tools for web searching via the Tavily API, dice rolling using standard notation, and cryptocurrency market data through the CoinGecko API. It is designed to integrate these capabilities into AI workflows using a standard input/output transport mode.
      3
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Exposes metasearch across many engines and a page-to-Markdown fetcher as two MCP tools, web_search and web_fetch, so any MCP client can run searches and pull clean article content on demand. It also supports news-focused queries with category and time-range filters, plus optional inline page content.
      AGPL 3.0