For SaaS developers · One integration · Every major AI client

Your API, inside every major AI.
No server to build.

AgentPlay reads your OpenAPI spec and hosts a live MCP gateway — so Claude, ChatGPT, Gemini, and any MCP-compatible client can call your real API. Zero changes to your existing backend.

Free plan · No credit card required · Live in under 5 minutes

Claude — custom connector
You

Convert this PDF report to DOCX and email it to the team.

Claude

Using convert_file from Acme API…

Using send_email from Acme API…

Done. Converted and sent to the team in 2.1 seconds.

● Livemcp.getagentplay.dev/acme-api/mcp

One MCP endpoint works with every major AI client

Claude
custom connectors
ChatGPT
MCP support
Gemini
MCP support
Cursor
MCP tools
Any MCP client
open standard

The problem

Your customers are using Claude, ChatGPT, and Gemini.
They want to use them with your product.

Giving them that is harder than it should be.

Weeks of infrastructure work

An MCP server needs auth, transport, tool schema definitions, rate limiting, and hosting. It's a full engineering project before a single user gets value.

🔑

Your upstream secrets in the wrong place

Passing API keys through your users' Claude sessions is a security liability. Keys belong in the gateway, not the prompt.

📉

No visibility once it's live

Which tools are agents actually calling? What's failing? Which users are hitting limits? You need answers before something breaks in production.

How it works

From spec to live MCP tool in under 5 minutes

Three steps. No infrastructure to manage. No code changes to your existing API.

01

Import your OpenAPI spec

Paste a URL, upload a file, or use our AI prompt to generate a spec from scratch. Our AI reads your endpoints, writes clean descriptions, and skips destructive operations by default.

02

Get your MCP endpoint

You get a unique, authenticated URL. Paste it into Claude, ChatGPT, Gemini, Cursor, or any MCP-compatible client. Tools are discovered instantly — no client code, no SDK, no configuration.

03

Ship with confidence

Real-time call logs, per-tool analytics, built-in rate limiting, and AES-256 encrypted credentials. Your upstream API key stays locked in our vault — never visible to end users.

Real-world example

A SaaS ships their Claude integration this afternoon — not next quarter

A file-conversion company wants their users to say “convert this PDF to DOCX” to Claude and get a real result back. Normally that's a multi-week engineering project. With AgentPlay, their developer does it between breakfast and lunch.

Try it with your API →
1

Paste OpenAPI spec URL into AgentPlay

1 min
2

AI curates convert_file, list_formats, get_status tools

2 min
3

Add MCP URL as a Claude custom connector

1 min
4

Users call the real API through Claude — done

✓ live

Features

Everything a production MCP server needs

Security, observability, and reliability — already built. You just connect your spec.

🤖

AI-powered spec ingestion

Drop in an OpenAPI URL or paste raw JSON/YAML. Our AI writes tool names, descriptions, and parameter docs — and disables destructive endpoints by default. Don't have a spec? Use our AI prompt to generate one.

🔐

Encrypted credentials vault

Your upstream API key is AES-256-GCM encrypted at rest and decrypted only inside the request handler. It never appears in logs, user sessions, or response payloads.

✏️

Full tool control

Rename tools, rewrite descriptions, enable or disable individual endpoints, and edit parameter documentation — all from the dashboard. Edits survive re-imports.

🛡️

SSRF protection built in

Every upstream URL is validated at config time and again at request time. Private IP ranges, localhost, and link-local addresses are always blocked.

Rate limiting & quotas

Sliding-window rate limiter per project and monthly quota counters. Requests over the limit get a clean 429 — your upstream API is never hammered by runaway agents.

📊

Real-time call logs

See every tool call as it happens. Per-tool counts, error rates, and latency in the dashboard. Know exactly how Claude is using your API — before issues reach your users.

Pricing

Simple, transparent pricing

Start free. Upgrade when you need more projects — calls are always generous.

Free

€0forever

Try AgentPlay risk-free with your first project.

  • 1 project
  • 5,000 calls / month
  • AI-powered spec ingestion
  • Encrypted credentials vault
  • Call logs
  • Community support
Start for free
Most popular

Pro

€19/month

For teams shipping their first production integration.

  • 3 projects
  • 100,000 calls / month
  • Everything in Free
  • Analytics dashboard
  • No AgentPlay branding
  • Email support
Get started

Team

€49/month

Scale across multiple products and teams.

  • 10 projects
  • Unlimited calls
  • Everything in Pro
  • Priority support
  • Higher rate limits
  • Team access (coming soon)
Get started

FAQ

Frequently asked questions

What exactly is MCP?+

MCP (Model Context Protocol) is an open standard that lets AI models call external tools and APIs in a structured, typed way. It was created by Anthropic and is now supported across Claude, ChatGPT, Gemini, Cursor, and a growing list of agent frameworks. AgentPlay hosts an MCP-compliant gateway for your API — one integration that works everywhere.

Do I need to change my existing API?+

No. AgentPlay sits in front of your API as a gateway. Your backend doesn't need to know anything about MCP, Claude, or AgentPlay. You just provide your OpenAPI spec and your API key — we handle the rest.

How does authentication work for my users?+

Your upstream API key stays in AgentPlay's encrypted vault — users never see it. Each of your users gets their own AgentPlay API key to connect their Claude account. When Claude calls a tool, AgentPlay authenticates to your API using the shared upstream credential. This makes it ideal for team or internal use where all users share the same access level.

How does a user actually connect their AI client to my API?+

For Claude: open Claude.ai → Settings → Custom connectors → Add new connector, paste the MCP URL, and authorize with an AgentPlay API key. For Cursor and other MCP clients the flow is similar — paste the URL, authenticate, done. The exact steps vary by client but the MCP URL is always the same.

What if I don't have an OpenAPI spec?+

We've got you covered. AgentPlay includes a ready-made AI prompt you can paste into Claude to generate a spec from a plain description of your API. Just describe your endpoints, and Claude will produce a valid OpenAPI 3.0 file you can import directly.

How are my API credentials protected?+

Credentials are AES-256-GCM encrypted before storage. They are only decrypted inside the request handler at runtime, inside the gateway process. They never appear in call logs, user sessions, or response payloads. The key material never leaves the server.

What happens when I hit my monthly call limit?+

Requests over the limit return a 429 with a clear error message. Your tools stay registered — agents just need to wait or you can upgrade to a higher plan to restore service immediately.

Your users are already asking for this.

Every week you wait is another week your API isn't inside Claude, ChatGPT, or Gemini. Start on the free plan — your first project is live in under five minutes.

Start for free →

Free plan · No credit card required · Cancel anytime

Have a question?

We'll reply within one business day.