MCP Servers

fly-mcp-gateway

Enables deploying an always-on Streamable HTTP MCP gateway on Fly.io with optional bearer token auth, so AI clients can connect to a reliable MCP endpoint.

Category

README

fly-mcp-gateway

Always-on Streamable HTTP MCP gateway for Fly.io. Use this instead of a flaky Cloudflare Tunnel (mcp.oceanways.online).

Endpoint: https://<your-app>.fly.dev/mcp
Health: https://<your-app>.fly.dev/health
Optional auth: Authorization: Bearer <MCP_API_TOKEN>

Deploy (once)

# 1. Install flyctl — https://fly.io/docs/hands-on/install-flyctl/
fly auth login

# 2. Clone
git clone https://github.com/hush759/fly-mcp-gateway.git
cd fly-mcp-gateway

# 3. Launch (creates app + deploys)
fly launch --copy-config --yes

# 4. Set a secret token (recommended)
fly secrets set MCP_API_TOKEN="$(openssl rand -hex 24)"

# 5. Redeploy if needed
fly deploy

Pick a unique app name when prompted (e.g. clipboardh-mcp or hush759-mcp).

Point Grok / Cursor at it

Replace the old oceanways URL with:

{
  "mcpServers": {
    "fly-gateway": {
      "type": "streamable-http",
      "url": "https://YOUR-APP.fly.dev/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN"
      }
    }
  }
}

Free plan notes

fly.toml sets:

auto_stop_machines = "off"
min_machines_running = 1

That keeps one machine running so MCP does not cold-start. Free allowance is limited — watch Fly billing so you do not exceed free credits.

Add tools

Edit server.js and register more server.tool(...) handlers, then:

git add -A && git commit -m "feat: more tools" && git push
fly deploy

Local test

npm install
MCP_API_TOKEN=dev node server.js
# curl http://localhost:8080/health

Recommended Servers

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B

Using MCP to run code via e2b.

Neon Database

MCP server for interacting with Neon Management API and databases

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.