AI Makerspace MCP Demo Server
This MCP (Model Context Protocol) server provides information retrieval and utility tools through AI agents via multiple API integrations:
Web Search - Search the web using the Tavily API
Roll Dice - Simulate dice rolls using standard notation (e.g., "2d6") with customizable roll counts
Number Fact - Get interesting mathematical or date-related facts using the NumbersAPI
Space Fact - Retrieve NASA's Astronomy Picture of the Day with title, date, description, and image URL
Animal Fact - Get fun facts about various animals (defaults to dog)
Science Term - Explain scientific terminology using Wikipedia summaries
The server runs in stdio transport mode and integrates with AI agents like LangGraph with GPT-4 for conversational interfaces.
Mentioned as a CLI tool requirement for Windows installation, allowing repository cloning and version control operations
Provides integration for building AI agent applications that can connect to and interact with MCP server tools through stdio transport
Enables creation of ReAct agents using GPT-4o model that can interact with MCP server tools for web search and other capabilities
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., "@AI Makerspace MCP Demo Server search for 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!
✅ Answer:
Added few new Apis in server.py.
Example:- like below
@mcp.tool()
def space_fact() -> str:
🏗️ Activity #2:
Build a simple LangGraph application that interacts with your MCP Server.
You can find details here!
✅ Answer:
This project includes a simple LangGraph client that connects to the MCP server and uses AI agents to interact with the tools.
Setup
Install dependencies:
uv syncSet up environment variables by adding your OpenAI API key to
.env:OPENAI_API_KEY=your_api_key_hereRun the LangGraph client:
uv run langgraph_client.py
How It Works
The LangGraph client:
Connects to your MCP server via stdio transport
Loads all available tools (e.g.,
web_search,roll_dice,number_fact)Creates a ReAct agent using
openai:gpt-4oDemonstrates tool usage with example queries
Available Tools
6 toolsanimal_factB
Get a fun fact about a given animal.
Inputs: animal. Returns: result
number_factC
Get an interesting fact about a number or date using NumbersAPI.
Inputs: query (required). Returns: result
roll_diceC
Roll the dice with the given notation
Inputs: notation (required), num_rolls. Returns: result
science_termB
Explain a science term using Wikipedia summaries.
Inputs: term (required). Returns: result
space_factA
Get NASA's Astronomy Picture of the Day (APOD) with its title, date, description, and image URL.
Inputs: no named parameters. 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 6 tools
Each tool has a clearly distinct purpose targeting different domains: animal facts, number facts, dice rolling, science terms, space facts, and web search. There is no overlap in functionality, making tool selection straightforward for an agent.
Most tools follow a consistent noun_verb or noun_noun pattern (e.g., animal_fact, number_fact, science_term, space_fact), but roll_dice and web_search deviate slightly with verb_noun structures. The naming is still highly readable and predictable overall.
With 6 tools, the server is well-scoped for a demo or utility server, offering a diverse set of fun and informational functions without being overwhelming. Each tool earns its place by covering a unique aspect of trivia, randomness, or information retrieval.
The server covers a broad range of trivia and search domains, but there are minor gaps in consistency—for example, some tools fetch facts (animal, number, space) while others perform actions (roll dice, search web). However, as a demo server, it provides a coherent set for exploration without dead ends.
Maintenance
Related MCP Connectors
Web search API and MCP server for developers building AI agents.
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.
Free web search for AI agents. No API key required. Hosted MCP in active development.
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.-
- FlicenseBqualityDmaintenanceEnables web search capabilities through the Tavily API, allowing users to search the internet for information using natural language queries. Serves as a demonstration and educational project for building MCP servers with external API integrations.3-
- FlicenseCqualityDmaintenanceEnables web search capabilities through the Tavily API, allowing users to search the web for information using natural language queries. Demonstrates MCP (Model Context Protocol) server implementation with stdio transport mode.4-