ARTie Retirement Guide MCP Demo
Synthetic MCP server that demonstrates retirement guidance capabilities including member profile, super balance, projections, insurance, and adviser booking for a ChatGPT connector demo.
README
ARTie Retirement Guide MCP Demo
Synthetic MCP server for demonstrating an ARTie Retirement Guide connector inside ChatGPT.
This project proves the experience pattern:
A member asks a retirement question in ChatGPT. ChatGPT connects to ARTie Retirement Guide. ARTie provides trusted retirement capabilities. ChatGPT answers in plain English.
The current data is synthetic only. This is not financial advice and does not connect to ART systems.
Current status
Working proof of concept:
- Runs locally with Node.js.
- Exposes a ChatGPT-compatible MCP endpoint at
/mcp. - Can be exposed temporarily with Cloudflare Tunnel.
- Has been successfully connected inside ChatGPT as
ARTie Retirement Guide. - ChatGPT can call the tools and answer the demo retirement question.
Run locally
node server.js
Local MCP URL:
http://localhost:8787/mcp
Health check:
http://localhost:8787/health
ChatGPT plugin fields
Name:
ARTie Retirement Guide
Description:
Provides synthetic retirement guidance for the ARTie concept demo.
Connection:
http://localhost:8787/mcp
Authentication:
No authentication
Demo prompt
I am Mia and I am 58 and exhausted. Can I afford to retire at 60?
This server uses fake member data only. It is not financial advice and does not connect to ART systems.
Available tools
get_member_profileget_super_balancerun_retirement_projectionexplain_insurancebook_advisermodel_part_time_transition
Temporary ChatGPT connection
For local testing, expose the local server with Cloudflare Tunnel:
.\cloudflared.exe tunnel --url http://localhost:8787
Use the generated HTTPS URL with /mcp:
https://example.trycloudflare.com/mcp
Do not use /sse for ChatGPT developer-mode apps. ChatGPT expects the /mcp endpoint.
Next direction
The next step is to remove the local dependency by deploying the server to a stable HTTPS host. See docs/NEXT_STEP_PLAN.md.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。