CustomMCPServer

CustomMCPServer

3.5

MCP servers are essentially how LLM and AI Tools communicate with each other. The Model Context Protocol allows applications to provide context for LLMs in a standardized way, separating the concerns of providing context from the actual LLM interaction.

CustomMCPServer is a Python-based server that leverages the Model Context Protocol (MCP) to facilitate communication between AI agents and LLMs. MCP servers are designed to expose data and functionality to LLM applications in a secure and standardized manner, similar to a web API but specifically tailored for LLM interactions. This server can be integrated with various platforms, such as Claude Desktop, to enhance AI capabilities by providing context and executing tasks. The server supports the creation of resources, tools, and prompts, allowing developers to automate processes and improve the efficiency of AI applications.

Features

  • Standardized Context Provision: MCP allows applications to provide context for LLMs in a standardized way, separating context provision from LLM interaction.
  • Secure Data Exposure: MCP servers expose data and functionality securely, similar to a web API but designed for LLM interactions.
  • Resource and Tool Creation: Developers can create resources and tools to load information and execute code, enhancing AI capabilities.
  • Integration with Platforms: The server can be integrated with platforms like Claude Desktop for seamless AI interaction.
  • Automation of Tasks: MCP servers enable automation of tasks, such as database operations, improving efficiency.

MCP Tools

  • AI Sticky Notes: A tool that allows users to create and manage sticky notes using AI capabilities.

Usage with Different Platforms

claude_desktop

bash
# create a uv-managed project
$ uv init .
Initialized project `custommcpserver` at `C:\Users\abhis\Desktop\AIAgents\CustomMCPServer`
# Then add MCP to your project dependencies:
$ uv add "mcp[cli]"
# activate python environment as well
$ source .venv/scripts/activate
# You can install this server in Claude Desktop and interact with it right away by running:
# mcp install main.py
# since we're in this vs code we do
$ uv run mcp install main.py
[04/16/25 10:06:31] INFO     Added server 'Demo' to Claude config
                    INFO     Successfully installed Demo in Claude app
# go to claude app > File > settings > Developer > Edit Config - opens up some file and open that claude_desktop_config.json file
# we can see the mcp run main.py(path) is added in that file.
# the mcp server should show up on claude app - if it's not - we do the following
# close claude app - open task manager and search fo claude and right click & do end task.
# wait a sec & open the app again
#  once the app loads , it spins up the mcp server and it shows on app - refer the image below & when you click on tool we can see the
# add tool and server:DEMO