---
title: "Deploy open-connector"
description: "connecting 1000+ SaaS providers to AI agents through MCP, HTTP, and OpenAPI"
category: "AI/ML"
url: https://railway.com/deploy/open-connector
---

# Deploy open-connector

connecting 1000+ SaaS providers to AI agents through MCP, HTTP, and OpenAPI

**[Deploy open-connector on Railway](https://railway.com/template/open-connector)**

- **Creator:** kmaki's Projects
- **Category:** AI/ML

## Template content

### app

- **Image:** xiaosong233/open-connector-railway:latest
- **Public domain:** Yes

## Documentation

# Deploy and Host OpenConnector on Railway

## About Hosting OpenConnector on Railway
OpenConnector runs on Railway as a single Docker image service with the bundled Web Console, HTTP runtime API, MCP endpoint, and SQLite-backed local state. Railway provides managed HTTPS, deploys from the prebuilt Docker Hub image, and mounts persistent storage for runtime data.

## Tech Stack
- Node.js 24 Alpine container
- Hono HTTP server
- React/Vite Web Console
- SQLite runtime storage
- MCP and OpenAPI-compatible runtime endpoints
- Railway service domain and persistent volume

## Why Deploy OpenConnector on Railway
Railway is a good fit for OpenConnector because the runtime is a single HTTP container that listens on port 3000 and stores all local state under one data directory. The template uses a prebuilt Docker image, avoids source builds, exposes a public HTTPS URL, and persists connection data on a Railway volume.

## Common Use Cases
- Browse connector providers and actions from the Web Console.
- Store API keys or OAuth client configuration for self-hosted connector workflows.
- Expose connector actions to apps through HTTP, OpenAPI, or MCP.
- Run a private connector runtime for teams that want control over credentials and storage.

## Deployment Notes
The app service uses the Docker image `xiaosong233/open-connector-railway:latest` built from upstream OpenConnector `v1.0.2`. It listens on `PORT=3000` and binds `HOST=0.0.0.0`. Runtime state, SQLite data, OAuth config, tokens, and transit files are stored in `/app/data`, which should be mounted as a Railway volume. `OOMOL_CONNECT_ORIGIN` should match the Railway public domain so OAuth redirects and generated file URLs use the correct HTTPS origin. Admin and runtime bearer tokens are generated as template secrets; users can view them in Railway variables after deployment.

## Dependencies for OpenConnector on Railway
OpenConnector only requires the app container and its persistent data volume for a one-click Railway deployment. No external database or Redis service is required.

### Deployment Dependencies

| Service | Image | Port | Volume |
|---------|-------|------|--------|
| app | xiaosong233/open-connector-railway:latest | 3000 | /app/data |

## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.
- [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

Open this page in a browser: https://railway.com/deploy/open-connector