mcp-boilerplate-integration
This project is a boilerplate for easily integrating with Claude.AI. It provides a working integration that operates out of the box for both desktop and web environments using Docker containers. By configuring environment variables, it can be quickly set up. However, it requires data backup and has known bugs that necessitate caution.
GitHub Stars
0
User Rating
Not Rated
Favorites
0
Views
35
Forks
0
Issues
0
Claude.AI Integration Boilerplate
You can run this to get a working Claude.AI Integration that works with Desktop and Web out of the box.
Just supply your values in .env and spin up the docker container by running docker compose up -d.
You will have to backup ./data, if you lose it, all your authenticated clients will get de-authenticated. Also Claude.AI is bugged as hell and will not allow clients to re-authenticate.
You will need some kind of reverse proxy that deals with TLS temination. I run my mcp servers on ports 7001, 7002, 7003, etc and then run a single Caddy instance mapping subdomains to local ports and deal with Let's Encrypt. If I lose the .data/ folder, i just spin up a new subdomain. It's the only way for Claude.AI to forget its cached client_id which will make it impossible for clients to re-authenticate.
You can run this stand-alone, I just don't like to clutter my OS with all the dependencies and thus keep it in a container.
28
Followers
9
Repositories
15
Gists
0
Total Contributions
🤩 Easy-to-use global IM bot platform designed for the LLM era / 简单易用的大模型即时通信机器人开发平台 ⚡️ Bots for QQ / QQ频道 / Discord / WeChat（微信）/ Telegram / 飞书 / 钉钉 / Slack 🧩 Integrated with ChatGPT（GPT)、DeepSeek、Dify、n8n、Claude、Google Gemini、xAI、PPIO、Ollama、阿里云百炼、SiliconFlow、Qwen、Moonshot(Kimi K2)、SillyTraven、MCP、WeClone etc. LLM & Agent & RAG