OpenConnector: One Gateway for Connecting AI Agents to 1,000+ SaaS Providers
OpenConnector is an open-source connector gateway for AI agents and apps that need access to user-authorized SaaS services.
It helps you connect accounts once, then expose a shared catalog of provider Actions through SDK, CLI, MCP, HTTP, or OpenAPI interfaces.
Key features:
• Connector catalog – the README lists 1,000+ providers and 10,000+ prebuilt Actions
• Multiple integration paths – use the Connector SDK, oo CLI, MCP, HTTP, or generated OpenAPI
• Credential handling – supports API keys, OAuth 2, custom credentials, and no-auth providers
• Inspectable Actions – review request/response schemas and required scopes before execution
• Deployment options – run locally with Docker or Node.js, or use OOMOL’s hosted runtime
It’s open-source (Apache License 2.0).
🔗 GitHub: https://lnkd.in/d-j_PGGx
⸻
♻️ Share this with your network if you found it useful or insightful.
✉️ If you’re into AI, ML, agents, and building real systems, join my newsletter (it’s free): dankornas.substack.com
Connecting an AI agent to multiple SaaS apps can become complicated when every provider requires its own authentication and integration logic.
OpenConnector is an open-source connector gateway designed to give AI agents and applications access to user-connected SaaS services through a common interface.
Instead of building separate integrations for every provider, OpenConnector provides a shared catalog of 1,000+ providers and 10,000+ prebuilt Actions, according to its current GitHub repository.
Key features include:
• Large connector catalog – Supports 1,000+ providers and 10,000+ prebuilt Actions.
• Multiple integration options – Actions can be accessed through the Connector SDK, oo CLI, MCP, HTTP APIs, and generated OpenAPI specifications.
• Credential handling – Supports API keys, OAuth 2, custom credentials, and no-auth providers. Credentials remain behind the runtime boundary rather than being exposed directly to the agent.
• Inspectable Actions – Developers can inspect Action schemas, required scopes, and execution information before using an Action.
• Self-hosting – OpenConnector can run on your own infrastructure, including local Docker/Node.js deployments, with additional deployment options such as Fly.io and Cloudflare-compatible infrastructure. OOMOL also provides a hosted runtime.
• MCP support – MCP-compatible agent hosts can interact with OpenConnector through its MCP endpoint and discover or execute Actions dynamically.
The project is open source and the GitHub repository is licensed under Apache-2.0.
In simple terms:
AI Agent → OpenConnector → Authentication & Policies → SaaS Action → Provider
That makes OpenConnector useful for agent applications that need controlled access to services such as Gmail, GitHub, Slack, Notion, Airtable, and other supported providers.