mcp-server-interview
Enables managing todo lists and tasks through natural language, supporting creation, status changes, and deletion.
README
mcp-server-interview
Model Context Protocol server for croonchloop interview
Usage
The following steps were how the server was tested.
First a client like claude desktop should be installed. Then open a terminal in the mcp-server-interview folder and execute:
Add MCP to your project dependencies:
uv add "mcp[cli]"
Then install the mcp server in claude:
uv run mcp install src/main.py
Structure
MCP-SERVER-INTERVIEW/
├── requirements.txt
├── .gitignore
├── config/
│ ├── conf.yml
| ├── loader.py
│ └── __init__.py
├── src/
| ├── dto/
| │ ├── lists.py
| │ └── tasks.py
| ├── service/
| | ├── __init__.py
| │ ├── todoList.py
| │ └── tasks.py
│ └── main.py
├── README.md
└── requirements.txt
Interacting with the server.
Examples of propts given to claude desktop to test and interact with the server. The prompts were given in spanish like the example of the challenge instructions.
Create a new todo list.
Crea una lista llamada 'Nombre de lista"
Create a task for a specific list.
Crea la tarea llamada 'tarea1' con descripcion 'desc' en la lista llamda 'Nombre de lista'
Start a task (change the task's status to 'InProgress')
Comenzar la tarea 'tarea1' de la lista 'Nombre de lista'
Complete a task (change the task's status to 'Completed')
Terminar la tarea 'tarea1' de la lista 'Nombre de lista'
Delete a task
Eliminar la tarea 'tarea1' de la lista 'Nombre de lista'
Next steps
Tasks: Right now it's not avilable to change name and description for a giving task.
Areas for improvement
Test: Even though the server was manually tested, testing the service layer will ensure correctness in futures changes.
App Configuration: After having dependency-related errors, the app configuration module was left out, and the todo list service url was hardcoded in the main script. However, keeping all configuration values in one place make te deployment and usage easier.
Project structure: Structuring a project in layers helps to assign responsabilities and group similar functions and classes. For this kind of project, it's not common to find a architecture design to follow.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.