Generate your OpenAPI spec straight from the API's docs with AI — no existing openapi.json required.
How it worksFeaturesPricingRoadmapDocs
Sign inCreate my MCP server →

Any API.
Connected to any LLM.
In 30 seconds.

Today, making an LLM talk to your API means writing an MCP server — one per API. We automate that: upload your OpenAPI spec, get a hosted MCP URL that works instantly in Claude, ChatGPT, Mistral, or any compatible client.

EU-hosted - GDPR-native - Your credentials never touch a US cloud
Create my MCP server — free →See how it works

No card required. 100 endpoints · 5,000 calls/month.

1 Spec in

2 Generated MCP server

GETlist_booksready
GETget_random_bookready
GETget_bookready
PATCHpatch_bookready
DELETEdelete_bookready
POSTcreate_bookready
GETget_inventoryready
+ 2 more
9 tools generated·—·v0.1
How it works

Three steps. Zero code.

You keep your API. We translate OpenAPI → MCP in real time — auth, schemas and errors preserved.

01

Import your OpenAPI

JSON or YAML, or a public HTTPS URL. OpenAPI 3.x and Swagger 2.0 — Postman collections coming soon.

library-openapi.json
9 endpoints3.1.0
02

We generate the MCP server

Every endpoint becomes a properly typed MCP tool. Auth is injected server-side, automatically.

// generated tool
tool list_books {
  genre?: string
  author?: string
  q?: string
} // from GET /books
03

Connect your LLM

Paste the MCP URL into your LLM (Claude, ChatGPT, Mistral, or any compatible client). Instant — and the URL stays stable when you update your spec.

CClaudeconnected
GChatGPTconnected
MMistralconnected
Before / after

One week of dev vs. thirty seconds.

The spec already exists. MCP boilerplate is repetitive and costly to maintain. Let us generate it — cleanly, on every release.

WITHOUT corelayer0

You write the MCP server by hand. Per API. Per version.

  • Redeclare every endpoint in TypeScript or Python
  • Rewire auth, types, pagination, error handling
  • Maintain it manually on every spec change
  • Deploy, monitor, manage secrets yourself
~1 week per API · ×N APIs

WITH corelayer0

You provide the spec. You get the MCP URL. Done.

  • Automatic generation from OpenAPI 3.x
  • Auth injected automatically
  • Update your spec anytime — stable MCP URL, connected LLMs don't break
  • EU-hosted (France 🇫🇷 - OVHcloud)
30 sec · any API
Under the hood

Everything you'll never have to write again.

Zero MCP infrastructure to maintain. Your API stays yours — auth, data, logic.

⌘

Auth injected automatically

Credentials never reach the LLM — they're injected server-side on every outbound call. No token, static Bearer, or OAuth2 Client Credentials — your choice.

No tokenpublic APIsavailable
API key / Bearerheader injectionavailable
OAuth2 Client Credentialsmachine-to-machineavailable
↻

Spec always in sync

Paste your JSON or point to an HTTPS URL. Update your spec anytime — the MCP URL stays stable, your connected LLMs don't disconnect.

30s
to generate an MCP server
stable
URL across spec updates
∞
endpoints supported
⊞

Endpoint filtering

Enable or disable each endpoint from the dashboard. Expose exactly what your LLM needs — nothing more.

◐

Native OAuth 2.1 per project

Each MCP server is its own Authorization Server. MCP clients connect without pre-shared tokens — PKCE S256, dynamic client registration, automatic rotation.

⌂

EU sovereignty by design

Hosted on OVHcloud (France 🇫🇷, EU), secrets encrypted under an EU-controlled KMS. Your data and credentials never leave the European Union — and never fall under the US CLOUD Act. GDPR-native, no transatlantic data transfer to assess.

⇄

A gateway between your APIs and every LLM

We speak MCP on the LLM side, plain HTTP/REST on your side. No agent to deploy, no SDK to integrate. Your LLM clients see tools; your API sees standard HTTP requests.

LLM CLIENTSClaude · Mistral Vibe · ChatGPT
— mcp →
CORELAYER0gateway · auth · MCP
— https →
YOUR APIunchanged
⚲

Secure by default

Credentials are never stored in plaintext. Argon2-hashed tokens, AES-256-GCM encryption under KMS, EU-only infrastructure.

Now available

What's already live.

Features already in production and ready to use today.

⊞Available

Classic Mode

One MCP tool per enabled endpoint. The LLM sees every operation directly in context. Simple, explicit — optimal below 20 endpoints.

λAvailable

Code Mode

Two fixed tools — search() to explore the OpenAPI spec, execute() to call the API. Constant token cost (~1,000 tokens) regardless of API size. Recommended above 20 endpoints.

↓Available

Spec import (JSON & YAML)

Paste your JSON or YAML spec, or point to a public HTTPS URL. OpenAPI 3.x and Swagger 2.0 supported. The spec is parsed server-side — it never enters the LLM context.

⚿Available

API token management

Static Bearer token encrypted server-side, injected automatically on every outbound call. The LLM never sees your credentials.

✨Available

Generate from docs

No published OpenAPI spec? Point us at the API's documentation pages (up to 5) and let an LLM (OVH AI Endpoints, gpt-oss-120b) draft one. Review and edit before creating the project — nothing is saved without your go-ahead.

On the roadmap

What's coming.

Our priority: broader format support and full observability of every LLM call.

◆Soon

Postman Collections

Import your Postman collections directly — no manual OpenAPI conversion.

◐Soon

Native observability

Structured logs, OpenTelemetry traces, replays. See what each LLM called, with which arguments, and what came back.

↺Soon

Git sync / webhooks

Connect your repo or a webhook. On every push, MCP tools regenerate automatically — the URL stays stable.

Pricing

Simple — the Free plan stays free.

Free

0€/ forever

Free, no card, no commitment.

  • 1 MCP project
  • Up to 100 active endpoints
  • 5,000 calls / month
  • Native OAuth 2.1 AS · PKCE · auto rotation
  • AES-256-GCM encryption under an EU sovereign KMS
  • EU-only infrastructure (France 🇫🇷)
Create my MCP server — free
FAQ

Frequently asked questions

Everything you need before connecting your first API.

Do my API data or credentials ever reach the LLM?

No. Credentials are encrypted server-side (AES-256-GCM under an EU-controlled KMS) and injected on each outbound call. The LLM sees tools and results, never your tokens or raw spec.

Which LLM clients are supported?

Any MCP-compatible client — Claude, ChatGPT, Mistral, and others. You paste one stable MCP URL; it keeps working even when you update your spec.

I don't have an OpenAPI spec — can I still use it?

Yes. Point corelayer0 at your API's documentation pages (up to 5) and an AI drafts an OpenAPI spec. You review and edit it before anything is saved.

Is my data really outside US jurisdiction?

Yes. Everything is hosted on OVHcloud (France, EU) with EU-only infrastructure — no transatlantic transfer, not subject to the US CLOUD Act.

Your API. Every LLM.
No MCP server to write.

Create my MCP server — free →

OpenAPI → MCP, in 30 seconds.
Built in Paris 🇫🇷 & hosted in the EU 🇪🇺

Product
  • Features
  • Pricing
  • Roadmap
Legal
  • Terms
  • Privacy
  • DPA
OVHcloud Startup Program Member
v0.1