MMCPMarkets
RM

revsmoke/mcpcfc

Developer tools

이 페이지는 AI로 자동 번역되었습니다. 기술적인 세부 사항은 원문을 확인하세요. 원문 보기

14 stars 5 forks 품질 65 트렌드 20MIT
Repository Install

A Remote Model Context Protocol (MCP) server for ColdFusion, enabling CFML applications to connect with Claude and other AI assistants.

개요

MCPCFC connects Adobe ColdFusion to Claude, ChatGPT, Cursor, VS Code, and any other AI assistant that supports the Model Context Protocol. It turns your existing CFML code into AI-callable tools — no rewrite required. Got a ColdFusion function that generates invoices? That's an MCP tool now. One that queries your proprietary database? Tool. One that kicks off an internal workflow? Tool. If ColdFusion can do it, AI can call it. Millions of lines of ColdFusion are still running in production — at government agencies, financial institutions, healthcare systems, and enterprises worldwide. That code works. But it's increasingly isolated from the AI-powered tools reshaping how people work. MCPCFC bridges that gap. Instead of rewriting your CF business logic in Python or TypeScript, you wrap it as an MCP tool and let AI assistants call it directly. Your legacy codebase becomes an AI-connected asset overnight.

README

원문 README의 일부입니다. 원문 보기.

MCPCFC — The World’s First ColdFusion MCP Server

Your ColdFusion apps can now talk to AI. And AI can use your CF tools.

MCPCFC connects Adobe ColdFusion to Claude, ChatGPT, Cursor, VS Code, and any other AI assistant that supports the Model Context Protocol. It turns your existing CFML code into AI-callable tools — no rewrite required.

Got a ColdFusion function that generates invoices? That’s an MCP tool now. One that queries your proprietary database? Tool. One that kicks off an internal workflow? Tool. If ColdFusion can do it, AI can call it.

┌─────────────┐      ┌──────────────┐      ┌──────────────────┐
│   Claude /   │─────▶│    MCPCFC     │─────▶│  Your CF App     │
│   ChatGPT /  │◀─────│  MCP Server   │◀─────│  & Business Logic│
│   Cursor     │      └──────────────┘      └──────────────────┘
└─────────────┘       JSON-RPC 2.0          PDF, Email, DB,
                      + Stdio Bridge        Files, HTTP, ...

Why this matters

Millions of lines of ColdFusion are still running in production — at government agencies, financial institutions, healthcare systems, and enterprises worldwide. That code works. But it’s increasingly isolated from the AI-powered tools reshaping how people work.

MCPCFC bridges that gap. Instead of rewriting your CF business logic in Python or TypeScript, you wrap it as an MCP tool and let AI assistants call it directly. Your legacy codebase becomes an AI-connected asset overnight.

Who this is for:

  • Enterprise teams sitting on years of CF business logic who want AI capabilities without a rewrite
  • Government agencies modernizing legacy CF systems incrementally
  • CF developers who want to build the next generation of intelligent applications on top of what already works
  • Digital transformation leads looking for a low-risk path from legacy to cutting-edge

What’s included

MCPCFC ships with six proof-of-concept tools that demonstrate the pattern:

Tool What it does
hello Simple greeting — useful for verifying connectivity
fileOperations Sandboxed file I/O (read, write, list, delete, exists, info)
httpRequest Outbound HTTP requests (blocks private/internal IPs)
pdf Generate, extract text from, and merge PDFs using ColdFusion’s built-in PDF engine
queryDatabase Validated read-only SQL queries (SELECT only)
sendEmail Send email via SendGrid (requires SENDGRID_API_KEY)

These are intentionally simple. The real power is in adding your own tools — see Adding a custom tool below.

Tested environment

  • ✅ macOS + Adobe ColdFusion 2025
  • ⚠️ Not yet tested on Windows/Linux or other CFML engines (Lucee, BoxLang, etc.)

Quick start

Option 1: Browser test client

  1. Clone this repo into your ColdFusion web root (or symlink it).
  2. Visit: http://localhost:8500/mcpcfc/client-examples/test-client.cfm
GitHub에서 전체 README 보기

설치

This server does not publish a one-line install command.

Open the repository installation guide MCP 초보자라면? mcpskill.org 가이드부터 시작하세요 →

설정

{ "mcpServers": { "coldfusion-mcp": { "command": "/absolute/path/to/mcpcfc/bridge/cf-mcp-bridge.sh", "env": { "MCPCFC_URL": "http://localhost:8500/mcpcfc" } } } }