LounasMCP
Enables retrieval of daily lunch menus for restaurants in Sello shopping center (Espoo) from lounaat.info.
README
LounasMCP
A Model Context Protocol (MCP) server that scrapes daily lunch menus for restaurants located in Kauppakeskus Sello, Espoo from lounaat.info.
Built using the official Anthropic MCP Python SDK's FastMCP and BeautifulSoup4.
Features
get_sello_lunch_menus: Retrieve Sello restaurant lunch menus.- Parameter:
day(optional): Query specific day (keskiviikko,torstai, etc.). Defaults to"today".
- Parameter:
- Flexible Transport: Natively supports both
stdioandssetransports. - Docker Support: Ready to be packaged and run in a containerized environment (ideal for connecting to LiteLLM).
Setup & Running Locally
Installation
Ensure you have Python 3.10+ installed.
# Create and activate virtual environment
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install package
pip install -e .
Running Server
By default, the server runs in stdio mode:
python server.py
To run in SSE mode (web server on port 8000):
python server.py --transport sse --port 8000
Running with Docker
1. Build the Docker Image
docker build -t lounas-mcp .
2. Run Options
Option A: stdio Mode (Direct Command via Docker Exec)
Your MCP client can invoke Docker directly:
docker run -i --rm lounas-mcp --transport stdio
Option B: SSE Mode (HTTP Server)
Expose the HTTP port so other containers or host services can connect via HTTP SSE:
docker run -d --name lounas-mcp -p 8000:8000 lounas-mcp --transport sse --port 8000
Connecting to LiteLLM
To integrate this MCP server with LiteLLM, you can configure the MCP settings depending on how your LiteLLM instance is running.
Using SSE (Recommended for Containerized Environments)
If your LiteLLM is running in a Docker container, run lounas-mcp in SSE mode (Option B above) on the same network. Then, add it to your LiteLLM configuration:
mcp_servers:
lounas-mcp:
type: sse
url: http://lounas-mcp:8000/sse
(If LiteLLM is running on the host machine and Docker port is mapped, use http://localhost:8000/sse)
Using stdio (If LiteLLM has docker-cli access)
If your LiteLLM server runs locally and can invoke docker directly:
mcp_servers:
lounas-mcp:
type: command
command: docker
args:
- run
- -i
- --rm
- lounas-mcp
- --transport
- stdio
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.