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.
You keep your API. We do the OpenAPI → MCP translation in real time — auth, schemas, errors preserved.
JSON or YAML, or a public HTTPS URL. OpenAPI 3.x and Swagger 2.0 — Postman collections coming soon.
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
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.
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.
You write the MCP server by hand. Per API. Every release.
You give us the spec. You get back the MCP URL. That's it.
Zero MCP infrastructure to maintain. Your API stays yours — auth, data, logic.
Credentials never touch the LLM — they are injected server-side on every outgoing call. OAuth2 Client Credentials coming soon.
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.
Enable or disable each endpoint from the dashboard. Expose exactly what your LLM needs — nothing more.
Each MCP server is its own Authorization Server. MCP clients connect without a pre-shared token — PKCE S256, dynamic client registration, automatic rotation.
Hosted on OVH Cloud, France region. Secrets encrypted via OVH KMS. Your data and secrets never leave France.
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.
Your credentials are never stored in plaintext. Tokens hashed with Argon2, secrets encrypted AES-256-GCM under KMS, 100% France-based infrastructure 🇫🇷.
Features already in production and ready to use today.
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).
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.
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.
Static Bearer token encrypted server-side, injected automatically on every outgoing call. The LLM never sees your credentials.
Our priority: broader format support and full observability for every LLM call.
Import your Postman collections directly — no manual conversion to OpenAPI required.
Structured logs, OpenTelemetry traces, replays. See exactly what each LLM called, with which arguments, and the result.
Connect your Git repo or a webhook. On every push, MCP tools are automatically regenerated — the URL stays stable.
Free throughout the Public Beta (v1.0 planned Q4 2026). No card, no commitment.
Early-adopter bonus: accounts created before v1.0 keep Pro-tier quotas for 6 months after launch — automatically, no action required.