Command Palette

Search for a command to run...

UnylyUnyly
Весь каталог

Remote Server

БесплатноНе проверен

Enables multi-user remote MCP interactions with Gmail, OpenAI, and Salesforce via a FastMCP server.

GitHubEmbed

Описание

Enables multi-user remote MCP interactions with Gmail, OpenAI, and Salesforce via a FastMCP server.

README

A production-style remote MCP (Model Context Protocol) server built with FastMCP, exposing tools over a multi-user, HTTP-streamable (resumable) transport and deployed to the cloud via CI/CD. It integrates Gmail, OpenAI, and Salesforce behind a clean service layer, with JWT-based Salesforce auth.

Part of the SunnyLab build series — the step that took a local MCP server to a resumable, multi-user remote server on cloud. Sanitized public showcase: all secrets, keys, and infra identifiers were removed; configure your own .env / CI secrets.

What it demonstrates

  • Remote MCP over HTTP-streamable, resumable transport (multi-user, not just local stdio)
  • FastMCP server exposing tools/services
  • Enterprise integrations — Gmail, OpenAI, Salesforce (JWT bearer flow; keys loaded from env/secret-mounted files at runtime, never committed)
  • Cloud-native delivery — Docker, Cloud Build, GitHub Actions (all secrets via ${{ secrets.* }}; project/VM are placeholders)
  • Log retention cron + a lightweight dashboard

Architecture

MCP clients (multi-user)
        │  HTTP-streamable / resumable MCP
        ▼
FastMCP remote server
   ├─ tools (gmail / openai / salesforce)
   └─ service layer  ──►  Gmail · OpenAI · Salesforce (JWT)
        │
        ▼
  deployed on cloud VM (Docker), CI/CD via GitHub Actions

See mcp_server/ for tools and services.

Tech stack

Python · MCP / FastMCP · HTTP-streamable resumable transport · Gmail/OpenAI/Salesforce integrations · JWT · Docker · Google Cloud Build · GitHub Actions

Project structure

mcp_server/      # FastMCP server, tools, services, config
generate_token.py# OAuth token helper (no secrets committed)
retention_cron.py# log retention job
dashboard.py     # lightweight dashboard
.github/         # CI/CD (secrets via ${{ secrets.* }}, placeholders for project/VM)
Dockerfile · docker-compose.yml · cloudbuild.yaml
.env.example     # required env vars (no real keys)

Setup

cp .env.example .env      # your own keys; SF JWT key path, OPENAI, Google …
pip install -r requirements.txt
# run the FastMCP server (see mcp_server/)

Note

Public portfolio showcase. Credential files (github-deploy-key.json, SF private key, tokens), .env, and infrastructure identifiers were removed before publishing. The code loads all secrets from environment / mounted files at runtime — none are committed.


SunnyLab — building agentic AI in public · Medium @sunnylabtv · YouTube @sunnylabtv

from github.com/sunnylabtv-crypto/ai_mcp_fastmcp_remote-public

Установка Remote Server

У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.

▸ github.com/sunnylabtv-crypto/ai_mcp_fastmcp_remote-public

FAQ

Remote Server MCP бесплатный?

Да, Remote Server MCP бесплатный — установка в пару кликов через Unyly без оплаты.

Нужен ли API-ключ для Remote Server?

Нет, Remote Server работает без API-ключей и переменных окружения.

Remote Server — hosted или self-hosted?

Доступен hosted-вариант: Unyly запускает сервер в облаке, локальная установка не обязательна.

Как установить Remote Server в Claude Desktop, Claude Code или Cursor?

Открой Remote Server на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.

Похожие MCP

Compare Remote Server with

Не уверен что выбрать?

Найди свой стек за 60 секунд

Автор?

Embed-бейдж для README

Похожее

Все в категории communication