Code Mode is now available — two fixed tools to call any API without flooding your LLM context.
How it worksFeaturesPricingRoadmap
Create my MCP server →

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

Today, for an LLM to talk to your API, someone has to write an MCP server — one per API. We automate that: drop in your OpenAPI spec, get back an MCP URL that works instantly in Claude, Mistral Vibe, ChatGPT, or any compatible client.

Try with my spec →Watch a demoNo card. 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 to write.

You keep your API. We do the OpenAPI → MCP translation in real time — auth, schemas, 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

Each endpoint becomes a typed tool tool. Auth injected automatically server-side.

// generated tool
tool list_invoices {
  customer_id?: string
  status?: "paid" | "open"
  limit?: number
} // from GET /books
03

Plug into your LLM

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

CClaudeconnected
GChatGPTconnected
MMistralconnected
Before / after

A week of dev vs. thirty seconds.

The spec already exists. The MCP code, on the other hand, 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. Every release.

  • Re-declare every endpoint in TypeScript or Python
  • Re-wire auth, types, pagination, errors
  • Maintain it manually every time the spec changes
  • Deploy, monitor, manage secrets yourself
~1 week per API · ×N apis

WITH corelayer0

You give us the spec. You get back the MCP URL. That's it.

  • Automatic generation from OpenAPI 3.x JSON
  • Auth injected automatically
  • Update spec at any time — MCP URL stays stable, connected LLMs don't drop
  • Hosted on 100% France-based infrastructure 🇫🇷
30 sec · any API
Under the hood

What you'll never have to write again.

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

⌘

Auth injected automatically

Credentials never touch the LLM — they are injected server-side on every outgoing call. OAuth2 Client Credentials coming soon.

No tokenpublic APIsavailable
API key / Bearerheader injectionavailable
OAuth2 Client Credentialsmachine-to-machine · M2Msoon
↻

Always up-to-date

Paste your JSON or point to an HTTPS URL. Update your spec at any time — the MCP URL stays stable, connected LLMs don't drop.

30s
MCP server generation
stable
URL on spec update
∞
supported endpoints
⊞

Filter endpoints

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

◐

Per-project OAuth 2.1 AS

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

⌂

Hosted in France 🇫🇷

Hosted on OVH Cloud, France region. Secrets encrypted via OVH KMS. Your data and secrets never leave France.

⇄

A gateway between your APIs and every LLM

MCP on the LLM side, HTTP/REST on the API 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
⚲

Security by default

Your credentials are never stored in plaintext. Tokens hashed with Argon2, secrets encrypted AES-256-GCM under KMS, 100% France-based 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 each operation directly in its context. Simple, explicit, optimal for small APIs (fewer than 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 when 20+ endpoints are enabled.

↓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 outgoing call. The LLM never sees your credentials.

On the roadmap

What's coming next.

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

◆Soon

Postman Collections

Import your Postman collections directly — no manual conversion to OpenAPI required.

◐Soon

Native observability

Structured logs, OpenTelemetry traces, replays. See exactly what each LLM called, with which arguments, and the result.

↺Soon

Git sync / webhooks

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

Pricing

Public Beta — everything is free.

Free

0€/ during the Beta

Free throughout the Public Beta (v1.0 planned Q4 2026). No card, no commitment.

  • 1 MCP project
  • Up to 100 enabled endpoints
  • 5,000 calls / month
  • Native OAuth 2.1 AS · PKCE · auto-rotation
  • AES-256-GCM encryption under sovereign KMS
  • 100% France-hosted 🇫🇷
Start free

Early-adopter bonus: accounts created before v1.0 keep Pro-tier quotas for 6 months after launch — automatically, no action required.

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

Generate my MCP server →

OpenAPI → MCP, in 30 seconds. Built in Paris, hosted in France 🇫🇷

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