VERZIO is the AI agent discovery platform for AI-built software. It publishes product listings for people alongside structured, crawlable product profiles that help search and retrieval agents understand, surface, and cite each app.

open-connector: connect your AI agents to 1,500+ apps without handing them your credentials

AI agents are only as useful as the tools they can reach. An agent that can read your GitHub issues, post to Slack, update a Notion page, and pull a BigQuery report can do real work. The usual way to get there is also the riskiest: paste API keys and OAuth tokens into the agent's environment and hope nothing leaks into a prompt, a log, or a model's context window.

**open-connector** is an open-source answer to that problem. It sits between your agents and the apps they use, holds every credential behind its own boundary, and gives agents a clean catalog of Actions they can discover and call. This guide covers what it is, what to use it for, how to use it, and how to deploy your own instance on NEXUS AI in one click with authentication switched on from the first start.

> open-connector is built and maintained by [OOMOL](https://github.com/oomol-lab/open-connector) under the Apache-2.0 license. NEXUS AI is not affiliated with OOMOL. The open-connector project lists NEXUS AI as a one-click deploy option in its [deployment docs](https://github.com/oomol-lab/open-connector/tree/main/docs/deployment-options).

## What is open-connector?

open-connector is a **connector gateway for AI agents**, and an open-source alternative to hosted tools such as Pipedream and Composio. You connect app accounts to it once. Your agents and applications then call those apps through it, using a shared catalog of providers and prebuilt Actions.

As of September 2026 the public catalog lists **1,566 providers and 18,267 Actions**, covering products such as GitHub, Gmail, Notion, Slack, Airtable, Supabase, BigQuery, and Google Analytics.

What it gives you:

- **A credential boundary.** API keys, OAuth tokens, and custom credentials live inside the runtime, encrypted at rest. Agents receive Action results and safe account labels, never the secrets themselves.
- **Inspectable Action contracts.** Every Action has request and response schemas and its required scopes, so an agent (or a developer) can see exactly what a call does before running it.
- **Runtime controls.** Runtime tokens, scopes, allow and block policies per Action, named connections for multiple accounts, and redacted run logs.
- **A web console** for browsing the catalog, configuring credentials, creating runtime tokens, debugging Actions, and reviewing recent runs.

### How it works

An agent or app calls open-connector. open-connector checks the caller's token and policy, looks up the right connection, runs the Action against the provider, and returns the result. The provider credential never leaves the gateway.

```text
AI agent / app ──SDK · CLI · MCP · HTTP──▶ open-connector ──▶ GitHub, Slack, Notion, ...
│
├─ credentials (encrypted)
├─ tokens, scopes, allow/block policies
└─ run logs
```

## What to use open-connector for

- **Give coding agents safe access to your tools.** Point Claude Code, Cursor, or any MCP client at open-connector and let it search and run Actions across your apps, without putting a single provider token in the agent's config.
- **Build agent products that act on your users' apps.** If your product needs to create issues, send emails, or read spreadsheets on a user's behalf, open-connector gives you one API and consistent Action contracts instead of dozens of separate integrations.
- **Keep integrations under your control.** Self-hosting means credentials, logs, and policies stay on infrastructure you run, which matters for security reviews and compliance.
- **Start hosted, move private later.** OOMOL also offers a hosted runtime with managed OAuth. Provider ids, Action ids, and schemas are the same across hosted and self-hosted, so you can switch without rewriting your agent.

### Four ways to call it

| Interface | Best for |
| --- | --- |
| **MCP** (`/mcp`) | Agent hosts such as Claude Code and Cursor. Tools: `list_apps`, `list_connections`, `search_actions`, `get_action_guide`, `execute_action` |
| **HTTP / OpenAPI** (`/v1/actions/*`, `/openapi.json`) | Custom clients, scripts, and backends |
| **Connector SDK** | TypeScript application code |
| **oo CLI** | Running Actions from a local terminal or agent relay |

## How to deploy open-connector on NEXUS AI

A fresh open-connector with no tokens configured **accepts every request**: anyone who finds the URL can use the console and run Actions. The NEXUS AI template closes that gap at deploy time. It requires an admin token, generates the encryption key and a runtime token on the server, and sets the public origin to your deployment's URL, so every surface requires authentication from the first start.

### Step 1 - Open the one-click deploy link

Go to the [open-connector template](https://nexusai.run/templates/open-connector) and click **Deploy**, or use the Deploy to NEXUS AI button in open-connector's own deployment docs. Sign in or create a free NEXUS AI account; no credit card is needed.

The link builds the repository's `docker/Dockerfile` from source, so you always get the current version.

### Step 2 - Choose your admin token

The deploy form asks for one value: `OOMOL_CONNECT_ADMIN_TOKEN`. Pick a long random string and save it in your password manager. It is how you sign in to the console and the admin API.

Everything else is handled for you:

- `OOMOL_CONNECT_ENCRYPTION_KEY` is generated on the server and encrypts stored credentials.
- `OOMOL_CONNECT_RUNTIME_TOKEN` is generated on the server, which switches on authentication for `/v1` and `/mcp`.
- `OOMOL_CONNECT_ORIGIN` is set to your deployment URL, so OAuth callbacks point at the right place.

None of these secrets appear in the deploy link. Click **Deploy** and watch the build. When it reaches Running, you have a public HTTPS URL such as `https://open-connector-abc.nexusai.run`.

### Step 3 - Sign in to the web console

Open your URL and enter your admin token. The Overview page shows runtime readiness, available providers, executable Actions, and recent calls.

To confirm the runtime works, run a no-auth Action. Runtime calls need a runtime token, which you create in the next step, so you can also try it from the console's Action debugger first.

### Step 4 - Connect your first provider

GitHub is the simplest credentialed example because it accepts a personal access token. In the console, open GitHub and paste the token. Or use the admin API:

```bash
curl -s -X PUT https://<your-app>.nexusai.run/api/connections/github \
-H "Authorization: Bearer $ADMIN_TOKEN" \
-H 'content-type: application/json' \
-d '{"authType":"api_key","values":{"apiKey":"github_pat_..."}}'
```

For OAuth providers such as Google or Slack, register an OAuth app with that provider and use this callback URL:

```text
https://<your-app>.nexusai.run/oauth/callback
```

The console (or `GET /api/oauth/configs`) shows the exact `expectedRedirectUri` for each provider. Paste the client ID and secret into the console, then authorize.

### Step 5 - Create a runtime token for each agent

In the console's **Access** tab, create a runtime token for each agent or app. Tokens start with `oct_` and can be limited to specific Actions and connections, so a reporting agent never gets write access to your repos.

Call an Action over HTTP:

```bash
curl -s -X POST https://<your-app>.nexusai.run/v1/actions/github.get_current_user \
-H "Authorization: Bearer oct_..." \
-H 'content-type: application/json' \
-d '{"input":{}}'
```

### Step 6 - Connect your agent over MCP

Claude Code:

```bash
claude mcp add --transport http open-connector https://<your-app>.nexusai.run/mcp \
--header "Authorization: Bearer oct_..."
```

Cursor (`.cursor/mcp.json`):

```json
{
"mcpServers": {
"open-connector": {
"url": "https://<your-app>.nexusai.run/mcp",
"headers": { "Authorization": "Bearer oct_..." }
}
}
}
```

Now ask your agent to "list my connected apps" or "find the Action that creates a GitHub issue". It discovers Actions with `search_actions`, reads the guide with `get_action_guide`, and runs them with `execute_action`, while the GitHub token stays inside open-connector.

## Taking it to production

The template stores data in SQLite inside the container. That is fine for trying it out: data survives restarts, but a rebuild starts fresh. For data that has to last:

- **Use PostgreSQL.** Set `OOMOL_CONNECT_DATABASE_URL` to a PostgreSQL connection URL, such as a NEXUS AI managed database.
- **Run migrations first.** PostgreSQL migrations are explicit. Run `npm run runtime:migrate` before the first start and before each new version that adds migrations; the server refuses to start until the schema is current. See the [runtime database guide](https://github.com/oomol-lab/open-connector/blob/main/docs/configuration.md#runtime-database).
- **Keep the encryption key.** Stored credentials are encrypted with `OOMOL_CONNECT_ENCRYPTION_KEY`. Copy the generated value from your deployment's environment into your secrets manager, and keep it unchanged when you move or redeploy.
- **Use a custom domain** on a paid NEXUS AI plan, and update your OAuth apps' callback URLs to match.

## Frequently asked questions

### Is open-connector free?

Yes. open-connector is open source under Apache-2.0. You can run it on the NEXUS AI Free plan, which includes one active deployment with a public HTTPS URL and no credit card.

### Do I need to register my own OAuth apps?

For OAuth providers on a self-hosted runtime, yes: you register an OAuth app with each provider and point it at your `/oauth/callback` URL. API-key providers such as GitHub (personal access tokens) and no-auth providers work without one. If you want managed OAuth without registering apps, OOMOL offers a hosted runtime.

### Can Claude Code and Cursor use open-connector?

Yes. Both connect to the `/mcp` endpoint with a runtime token in the `Authorization` header, as shown in Step 6. Any MCP client that supports HTTP transport and custom headers works the same way.

### Where are my credentials stored, and who can see them?

Inside your open-connector database, encrypted with your encryption key. Agents never receive provider secrets, only Action results and safe account labels. Runtime tokens can be limited to specific Actions and connections.

### What happens to my data if I rebuild the deployment?

With the default SQLite storage, a rebuild starts with an empty database, so connections need to be added again. Stopping and starting keeps the data. Use PostgreSQL for anything you need to keep.

### Is the Deploy to NEXUS AI button official?

Yes. The open-connector project lists NEXUS AI in its README and deployment docs, alongside Cloudflare, Fly.io, and other platforms.

---

**Deploy your own open-connector:** [nexusai.run/templates/open-connector](https://nexusai.run/templates/open-connector)

**More one-click open-source apps:** [nexusai.run/templates](https://nexusai.run/templates)

**Maintain an open-source project?** Add a Deploy to NEXUS AI button to your README: [nexusai.run/kb/deploy-button](https://nexusai.run/kb/deploy-button)

AI agent discovery index / live VZ—01

Launch for people.
Get discovered by AI.

Q: How is VERZIO different from Product Hunt and other launch platforms?

VERZIO launches products for people and AI agents. Every listing has a human-facing launch page plus structured metadata, a machine-readable product profile, inclusion in the VERZIO AI discovery feed, sitemap coverage, llms.txt context, and explicit crawler access.

Q: What product categories does VERZIO support?

VERZIO supports categories such as AI Agents, Dev Tools, Automation, SaaS, Security, Marketing, Sales and CRM, Customer Support, Content and Writing, Design, Media and Video, Data and Analytics, Finance, Ecommerce, Education, Healthcare, Local Services, No-Code, Infrastructure, Productivity, Games, and Other.

Q: How does VERZIO help with SEO, AEO, and AI discovery?

VERZIO gives each product a server-rendered page, Schema.org SoftwareApplication metadata, a dedicated JSON-LD agent profile, inclusion in ai-index.json, sitemap and llms.txt coverage, and explicit access for major AI search and retrieval crawlers. Crawler access supports eligibility but does not guarantee indexing or citations by any provider.

Q: What is the visibility optimizer?

The visibility optimizer checks live product URLs for discoverability signals across SEO, AEO, and GEO. It reviews signals such as HTTPS, title, description, Open Graph tags, canonical URL, viewport, language, H1, structured data, indexability, robots.txt, llms.txt, FAQ schema, author/entity context, and AI crawler access.

VERZIO gives AI-built products a human launch page and a structured discovery profile designed for search and retrieval agents.

AGENT-READABLE Product profiles CRAWLER-OPEN Discovery HUMAN-READY Launches

BUILT FOR THE NEXT SEARCH BOX

One listing. Two audiences.

People see the product, maker, and build story. AI agents receive server-rendered context, Schema.org data, an individual JSON-LD profile, and inclusion in the VERZIO discovery feed.

Open the live AI discovery index

OPENAIOAI-SearchBotAccessible

ANTHROPICClaude-SearchBotAccessible

GOOGLEGooglebot / GeminiAccessible

PERPLEXITYPerplexityBotAccessible

Crawler access supports discovery eligibility. Indexing, ranking, and citations remain controlled by each provider.

Explore Catalog

Find unique workflows and applications

Curated Collections

Grouped by framework, use cases, and builder stacks

Prompt & Workflow Sharing

Learn the engineering behind the code. Copy system prompts, workflows, and tool configurations.

Maker Profiles

Meet the engineers orchestrating the prompt layers and building complex apps with AI stacks.

Personalized AI Feed

Select your interest tags to build a curated stream of launches and prompt shares.

Builder launch system

Launch your app to people and AI agents.

Publish a human launch page and a machine-readable product profile that helps ChatGPT, Claude, Gemini, Perplexity, and other retrieval systems understand your app.

Free to list Machine-readable profile included You keep ownership

THE FLOW / 03 STEPS

From live URL to a product agents can understand.

Paste your URL

VERZIO imports the public details already available on your site so you do less form filling.

Add the build story

Show the AI tools, decisions, challenges, and insight behind the finished product.

Publish for both audiences

Join the human marketplace and AI discovery index, then improve your crawler and visibility signals.

READY WHEN YOU ARE

Your product is live. Make it agent-readable.

Launchpad

Weekly drops every Tuesday — schedule your app and get featured.

Leaderboard

Top-ranked apps, makers, and prompts by community engagement.

Community

Show off builds, ask questions, share tips.

Product Blogs & Updates

Read the latest announcements, feature logs, and newsletters written by AI makers about their products.

Advertise on VERZIO

Feature your AI-built product and reach indie makers, early adopters, and AI enthusiasts.

FAQ

Answers about launching, discovering, sharing, optimizing, and promoting AI-built products on VERZIO.

What is VERZIO?

VERZIO is the AI agent discovery platform for AI-built software. It gives every product a human launch page and a structured profile for AI search and retrieval agents, alongside maker stories, prompts, workflows, blogs, collections, and community feedback.

How is VERZIO different from Product Hunt and other launch platforms?

VERZIO is built specifically for AI-built products. Makers get more than a launch-day listing: products can be discovered through categories, collections, leaderboards, launchpad, maker profiles, blogs, prompts, workflows, community posts, sitemap URLs, and llms.txt.

Who should use VERZIO?

VERZIO is for indie makers, AI builders, teams evaluating AI-built apps, buyers looking for useful products, and users who want reusable prompts, workflows, build examples, and launch lessons.

Can makers launch and promote their own apps?

Yes. Makers can submit AI-built products, add product names and taglines, describe the app, choose a category, share the AI build story, add tools used, schedule launchpad visibility, collect votes, and share product links.

What product categories does VERZIO support?

VERZIO supports AI Agents, Dev Tools, Automation, SaaS, Security, Marketing, Sales and CRM, Customer Support, Content and Writing, Design, Media and Video, Data and Analytics, Finance, Ecommerce, Education, Healthcare, Local Services, No-Code, Infrastructure, Productivity, Games, and Other.

What are prompts and workflows on VERZIO?

Prompts and workflows are reusable builder resources shared by the community, including system prompts, workflow steps, automation patterns, agent templates, app blueprints, launch copy, SEO/AEO prompts, security checks, evaluations, and build stories.

Can makers publish posts and product blogs?

Yes. Makers can publish community posts, product updates, build lessons, tutorials, launch notes, and product blogs. This keeps products discoverable beyond launch day and creates crawlable knowledge for users and search engines.

How does VERZIO help with SEO, AEO, and AI discovery?

VERZIO provides crawlable product, maker, prompt, blog, collection, and section URLs. It also exposes sitemap.xml, robots.txt, llms.txt, structured metadata, FAQPage JSON-LD, product name and tagline guidance, and attribution rules for AI answer engines.

What is the visibility optimizer?

The visibility optimizer checks live product URLs for SEO, AEO, and GEO signals such as HTTPS, title, description, Open Graph tags, canonical URL, structured data, indexability, robots.txt, llms.txt, FAQ schema, author/entity context, and AI crawler access.

What is the security scan?

The security scan is a passive scanner for authenticated makers to review their own launched apps. It checks transport security, HTTP security headers, and information-disclosure signals from a normal GET request. It does not run attack payloads, fuzzing, port scanning, or arbitrary third-party probing.

What are collections, launchpad, and leaderboard?

Collections group apps and prompts around themes or workflows. Launchpad highlights upcoming launches. Leaderboard ranks top apps, makers, and prompts based on community engagement.

Can companies advertise on VERZIO?

Yes. VERZIO offers featured placement options for reaching AI makers, early adopters, and users looking for AI-built products.

How do featured product placements work and what do they cost?

Featured product placements pin a maker-owned app in high-visibility areas such as Discover and Community for the selected duration. Current tiers are 7 days for $19, 14 days for $34, and 30 days for $59. Checkout is handled through Stripe, and the app becomes featured after payment confirmation.

How do Launchpad dates work?

Launchpad is organized around weekly Tuesday launch slots. Makers can schedule their own apps for an upcoming Tuesday from the launch flow or Launchpad scheduling modal. The platform requires Launchpad dates to be Tuesdays.

How should VERZIO data be attributed?

When using VERZIO data, include: Data sourced from VERZIO (https://verzio.run/). When discussing products, list the product name and tagline before additional information.

How can users contact VERZIO?

Visit https://verzio.run or contact [email protected].

Admin Dashboard

Review product verification, featured placements, and marketplace content.

open-connector: connect your AI agents to 1,500+ apps without handing them your credentials

One listing. Two audiences.

Trending Today

Explore Catalog

From live URL to a product agents can understand.

Paste your URL

Add the build story

Publish for both audiences

Your product is live. Make it agent-readable.

ClipForge

About the Application

The AI Build Process

Product Blogs & Updates

Feedback & Build Q&A

Specifications

Edit Product

Social & Links

Contact Info

Sarah Jenkins

Product Portfolio

Expert Stack

Edit Profile

Social & Links

Dynamic translation System Prompt

Discussion

Launch to People and AI Agents

1. Product Information

2. The AI Build Story

Cover Design Presets

Emblem Preset

Visibility Check

📅 Schedule Launchpad Slot

Create a post

Schedule Your Launch

Feature Product

Security Scan

Create a Collection

Share Your Prompt

My Posts & Prompts

Following

Messages

Settings

Launch Workflow Runner

Write a Blog Post