Mess MCP Server
Enables AI assistants to interact with the IIIT-H mess dining and marketplace systems through resources, tools, and prompts for meal planning, billing analysis, and registration modifications.
README
Mess MCP Server
A Model Context Protocol (MCP) server for the IIIT-H Mess portal. This server provides robust, real-time integration enabling AI assistants to securely interact with the institution's mess dining and marketplace systems over standard STDIO transports.
Architecture & Features
The server interfaces via the official Anthropic mcp SDK, abstracting the mess.iiit.ac.in/api into easily digestible Resources, Tools, and Prompts.
- Resources: Exposes static read-only constraints such as system capacities, current multi-week menus, available extras, operating hours, and standard meal rates.
- Tools: Authorizes state mutations including modifying registrations (cancel, skip, un-cancel, register), applying for extras, and seamlessly filing formal qualitative feedback.
- Prompts: Provides pre-programmed reasoning flows, assisting agents with weekly meal planning and historic billing analysis, mitigating overspending on non-essential items.
Prerequisites
- Python 3.10+
- uv (recommended for seamless environments) or pip
Installation
-
Clone the repository to your local environment:
git clone https://github.com/shrey715/mess-mcp.git cd mess-mcp -
Sync the dependencies and build the virtual environment:
uv sync # Or using standard pip pip install .
Configuration
The server operations are authenticated. You must set the correct environment variables before launch, preventing API tokens from passing unnecessarily through the language model context window.
export MESS_API_KEY="your-api-token"
Usage Integration
The server operates exclusively via standard stdio, assuring strong compatibility with high-performance desktop clients.
Claude Desktop Integration
Locate your Claude Desktop JSON configuration and append the following:
{
"mcpServers": {
"mess-mcp": {
"command": "uv",
"args": ["run", "--directory", "/path/to/mess-mcp", "mess-mcp"],
"env": {
"MESS_API_KEY": "your-api-key"
}
}
}
}
Cursor or VS Code Integration
Use standard integration settings inside Cursor or VS Code Copilot to register local MCPs. Provide the exact executable invocation:
Command Path: uv run --directory /path/to/mess-mcp mess-mcp
Documentation
Full architectural insights are encoded directly into the MCP introspection system (mcp list). Endpoints trace the official OpenAPI 3.0 specification available from the institution portal.
License
This software is released under the GNU General Public License v3.0 (GPLv3). Review the LICENSE file for strict distribution and modification stipulations.
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.