Frontend-Agnostic MCP Server
@tonton2006
About Frontend-Agnostic MCP Server
Test repository for MCP server
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"frontend-agnostic-mcp-server": {
"type": "http",
"url": "http://localhost:8000"
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Frontend-Agnostic MCP Server?
Frontend-Agnostic MCP Server is a Multi-Core Processing (MCP) server that exposes an add tool for adding two numbers via a Boomi integration, with a local fallback. It is designed to work with any frontend that supports the MCP protocol, not just Claude Desktop.
How to use Frontend-Agnostic MCP Server?
Install dependencies (pip install mcp-server requests python-dotenv), create a .env file with your BOOMI_TOKEN, and run python mcp_server.py. Optional arguments --host (default 0.0.0.0) and --port (default 8000) are available. The server can be called via a Python client (client.add(a=5, b=10)) or via HTTP POST to /v1/tools/add.
Key features of Frontend-Agnostic MCP Server
- Works with any MCP-compatible frontend
- Exposes a single
addtool for number addition - Connects to a Boomi integration for computation
- Falls back to local calculation if Boomi fails
- Configurable host and port via command-line arguments
- Explicit
mcp.serve()call and proper module structure
Use cases of Frontend-Agnostic MCP Server
- Adding two numbers through a Boomi integration process
- Demonstrating MCP server compatibility with various frontends
- Fallback arithmetic when external service is unreachable
- Lightweight tool for testing or prototyping MCP workflows
FAQ from Frontend-Agnostic MCP Server
What does the server actually do?
It provides an add tool that sends two numbers to a Boomi integration for summation. If the Boomi service fails, it calculates the sum locally as a fallback.
What dependencies and runtime are required?
The server requires Python, plus the packages mcp-server, requests, and python-dotenv. A Boomi API token must be set in a .env file as BOOMI_TOKEN.
Where does the data live?
Numbers are sent to a remote Boomi integration process for addition. The server can also perform the calculation locally if the Boomi service is unavailable.
What transport and authentication does it use?
The server uses HTTP transport (default port 8000). Authentication is handled via a BOOMI_TOKEN environment variable passed to the Boomi integration.
What are the known limits?
The server only exposes one tool (add). It requires a Boomi token to function with the remote integration; without it, only the local fallback works. The local fallback is simple arithmetic with no error handling beyond basic addition.
Frequently asked questions
What does the server actually do?
It provides an `add` tool that sends two numbers to a Boomi integration for summation. If the Boomi service fails, it calculates the sum locally as a fallback.
What dependencies and runtime are required?
The server requires Python, plus the packages `mcp-server`, `requests`, and `python-dotenv`. A Boomi API token must be set in a `.env` file as `BOOMI_TOKEN`.
Where does the data live?
Numbers are sent to a remote Boomi integration process for addition. The server can also perform the calculation locally if the Boomi service is unavailable.
What transport and authentication does it use?
The server uses HTTP transport (default port 8000). Authentication is handled via a `BOOMI_TOKEN` environment variable passed to the Boomi integration.
What are the known limits?
The server only exposes one tool (`add`). It requires a Boomi token to function with the remote integration; without it, only the local fallback works. The local fallback is simple arithmetic with no error handling beyond basic addition.
Basic information
More Developer Tools MCP servers
MCP Unity Editor (Game Engine)
CoderGamesterModel Context Protocol (MCP) plugin to connect with Unity Editor — designed for Cursor, Claude Code, Codex, Windsurf and other IDEs
FastAPI-MCP
tadata-orgExpose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
mcp-excalidraw
yctimlinMCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.
TalkToFigma
sonnylazuardiTalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
AptiBuild AI — Career Intelligence
ParklandBuildsAptiBuild AI MCP Server — career, labor market, and business idea intelligence for AI agents. 11 tools covering real-time FRED labor market signals, BLS wage data (126 occupations), AI-generated app ideas, career paths,
Comments