Host a remote MCP server

How to turn your API into an MCP server today?

Wrap each of your API’s routes as a tool, speak the MCP protocol, and put it online at an address AI assistants like Claude can reach.

The wrapping is the quick part. Keeping it online and safe is what takes weeks. Here’s why, and the easy way to solve it.

Skip to the one-command way
1 Why it’s hard

Writing it is the small part. Running it is the rest.

Once your MCP server is on the internet, anyone can call it, at any hour, as often as they like. It needs every layer below to stay safe, and each one keeps needing attention after launch.

What people see

MCP: Users can safely chat with your API

What it takes, under the water

  1. Speak the MCP protocolYou · 3–5 days
  2. Turn your routes into toolsYou · 2–4 days
  3. Sign-in that AI clients acceptYou · 1–3 weeks
  4. Limits for assistants stuck in a loopYou · 1–2 days
  5. A record of every callYou · 1–2 days
  6. Versions and rollbackYou · 2–3 days
  7. Scaling for traffic spikesYou · 1–2 days
  8. HTTPS and a domainYou · 2–4 hours
  9. Servers to run it onYou · 1–2 days
  10. Your APIalready yours
  11. Your backendalready yours
About 3–7 weeks of work, then keeping it running

Times are rough estimates for one experienced developer, including testing. They cover building it once; patching, scaling and watching it afterwards is ongoing work on top.

Skip those layers, and this is a normal morning

Most hosting puts your server online and stops there. With nothing checking who calls or how often, strangers get in and a looping agent crowds out your real users.

One morning, hosted bare

4 calls. 4 problems.

  • A stranger cancelled a real booking
  • Every customer’s bookings got out
  • One looping agent took the server down
  • Ana, a real user, was locked out

And no record of any of it.

What your server sawTuesday morning
  1. 09:14 Unknown callercancel_bookingDone. A stranger cancelled a booking.
  2. 09:15 Unknown callerlist_bookingsEvery customer’s bookings, handed over.
  3. 09:20 Agent in a looplist_bookings ×1,200Server overwhelmed.
  4. 09:31 Ana, via Claudelist_bookingsTimed out. Ana can’t get in.
There’s a shorter way.
2 The shortcut

Put your MCP server online with one command

APIblaze runs every layer of that stack for you. Point it at your API:

Put an MCP server online

$ npx apiblaze@latest create --target https://ninopizzas.com/openapi.yaml

Paste it in a terminal. No sign-up, no servers. The link is a sample restaurant API; swap in your own API’s address. It prints the MCP address to paste into Claude.

How can one command replace a whole stack?
3 Why it works

APIblaze is an API proxy: every request passes through it first

It sits between AI assistants and your API. Claude, Cursor or an agent calls APIblaze, and APIblaze passes on only the calls that are allowed, as ordinary requests to your API.

Callers

  • Ana, via Claudeasks to list her bookings
  • Unknown callerasks to cancel a booking
  • An agent in a loopasks to list bookings ×1,200

APIblaze

The API proxy

Speaks MCP to the assistant, checks who is calling and how often, then makes one ordinary call to your API.

Slowed to 10 a second

Your API

Only sees the calls APIblaze lets through.

Never reached your code.

That’s why it can stand in for the whole stack. Every assistant has to come through it, so it’s the one place to speak MCP, check sign-in and limits, and keep a record, while your API stays exactly as it is.

The same morning, on APIblaze

4 calls. All handled.

  • Both strangers were asked to sign in
  • The looping agent was slowed to 10 a second
  • Ana got her 2 bookings
  • The strangers never reached your API

And every call is on record.

APIblaze request logTuesday morning
  1. 09:14 Unknown callercancel_booking401 · sign in first
  2. 09:15 Unknown callerlist_bookings401 · sign in first
  3. 09:20 Agent in a looplist_bookings ×1,200429 · slowed to 10 a second
  4. 09:31 Ana, via Claudelist_bookings200 · her 2 bookings
Here is what setting it up looks like.
4 How to do it

Your API as an MCP server, step by step

  1. 1

    Start from wherever your API is

    APIblaze runs the MCP server; your API stays where it is. Pick the one that matches yours.

    Your API is deployed somewhere. Point APIblaze at its address or its OpenAPI description.

    $ npx apiblaze@latest create --target https://ninopizzas.com/openapi.yaml

    Prints an MCP address to paste into Claude, Cursor or Codex.

  2. 2

    Paste the address into Claude

    The command prints an MCP address. Add it in Claude as a custom connector, or in Cursor or Codex. People sign in the first time they use it, and every call after that is theirs.

  3. 3

    Every call goes through the same checks

    Ana asks Claude for her bookings at a restaurant whose API runs on APIblaze.

    Ana asks Claude: “show my bookings”

    1. tools/call list_bookingsfrom Claude, for Ana
    2. Signed inAna, through GitHub
    3. Allowedcustomers see their own bookings
    4. Under the limitwell inside 10 a second
    5. Your APIone ordinary GET /bookings
    6. Answeredher 2 bookings, back to Claude
    7. Loggedwho, what, the answer, how long
    • Sign-in, rules and limits run in APIblaze

      On Cloudflare’s network, close to whoever is calling. Your API only sees requests that passed.

    • Your API gets one ordinary request

      No MCP code in it, no session handling, no token checks. It answers the way it always has.

    • Every call leaves a record

      Who asked, for what, the answer and how long it took, ready when something looks wrong.

  4. 4

    Every assistant connects, whatever MCP version it speaks

    MCP has been updated four times since late 2024, and each assistant speaks the version it was built for. APIblaze speaks all of them, so Claude, Cursor, Codex and the rest all connect.

    1. 2024-11-05the first
    2. 2025-03-26supported
    3. 2025-06-18supported
    4. 2025-11-25supported
    5. 2026-07-28latest
    Connects withClaudeCursorCodexAny MCP client

Common questions

How do I host a remote MCP server without running infrastructure?

Put APIblaze in front of your API. One command gives you a live MCP address on Cloudflare’s global network, with sign-in, rules, limits and logs built in, and no servers, containers or certificates for you to manage.

What is a remote MCP server?

An MCP server that AI assistants reach over the internet by its address, instead of one that runs on the same computer as the assistant. Claude’s custom connectors, for example, connect to remote servers.

What is an API proxy?

A service that sits in front of your API. Every request goes through it first, so it can check who is calling and what they may do before your code runs. APIblaze is an API proxy that also speaks MCP.

Do I still need to host my API?

Yes. APIblaze runs the MCP server and everything in front of your API, not the API itself, which can live anywhere with an address: a cloud function, a container or a service you already run. While you build, the dev command serves it straight from your laptop.

Which AI clients can connect?

Any MCP client, including Claude, Cursor and Codex. APIblaze speaks every MCP version from 2024-11-05 to today’s, so a client pinned to an older version still connects.

Can I use my own domain?

Yes. Keep the address APIblaze gives you, or bring your own domain: APIblaze shows the DNS records to set and manages the certificates.

What does it cost?

There is no subscription and no monthly minimum. You pay per request from prepaid credits, with sign-in and permissions included in the price.

Prices are on the pricing page.

Put your MCP server online today

One command, no sign-up, nothing to keep running.

$ npx apiblaze@latest create --target https://ninopizzas.com/openapi.yaml
Using an AI coding assistant? Paste this into Claude Code or Codex:Host my API as a remote MCP server using npx apiblaze@latest skills