← Back to directory
O

OpenConnector

Community
Connect once. Use everywhere.
GitHub source repository ↗
★ 3.1k Stars Category · Other Very popular
52FMRS · D
Reliability
8/20
Security and permissions
10/20
Maintenance
10/20
Documentation
13/20
Setup experience
11/20

The source describes OpenConnector as an open-source, self-hosting-compatible connector gateway supporting MCP, HTTP, OpenAPI, an SDK, and a CLI, with credential, policy, Action-contract, and run-log management. It does not provide specific MCP tool identifiers, client compatibility details, or a client installation configuration, so those fields remain empty.

Read the FMRS scoring method →

OpenConnector is an open-source connector gateway for AI agents. It connects more than 1,000 SaaS providers and exposes more than 10,000 prebuilt Actions through an SDK, CLI, MCP, HTTP, and OpenAPI. The runtime manages credentials, OAuth, scopes, policies, and run logs, and supports local, Docker, Fly.io, Cloudflare-compatible, and OOMOL-hosted deployments.

Tools

The tool list has not been reviewed yet.

Setup

The repository provides a Docker Compose startup path: run docker compose up. Alternatively, use Node.js 22 or newer, install dependencies, and run npm run dev. The local console and API documentation are then available from the runtime. The source does not provide a specific MCP client configuration example.

Fit and risk

Best for

  • Agent products that need access to many SaaS, developer, data, or communication services
  • Teams that need inspectable Action request and response contracts
  • Developers and teams that want control over credentials and runtime deployment

Not for

  • Simple integrations that need only one service and no connector gateway
  • Users who require a documented list of specific MCP tool identifiers or client integrations
  • Users who do not want to manage credentials, deployment, or runtime configuration

Required permissions

  • API keys, OAuth clients, and provider-specific scopes may need to be configured
  • The runtime may require connections, runtime tokens, and Action allow or block policies
  • Required permissions depend on the connected provider and executed Action

Risks and side effects

  • Connected third-party accounts may let an agent access or modify user data
  • Incorrect scopes, Action policies, or runtime-token settings may broaden access
  • Credentials, transit files, and run logs must be protected in the deployment environment; logs support redaction but still require review
  • Third-party provider APIs, permissions, and availability can affect execution results

Troubleshooting

  1. Confirm that Node.js 22 or newer is installed
  2. Check that the runtime listens on http://localhost:3000 and the development console uses http://localhost:5173
  3. Review provider credentials, OAuth settings, scopes, and connection aliases
  4. Check runtime tokens and Action allow/block policies
  5. Inspect the console’s runtime overview, recent failures, and run logs
  6. For hosted deployments, confirm required migrations, secrets, and platform resources are configured

Use cases

Give AI agents durable access to users’ SaaS applications
Execute connector Actions through MCP, HTTP, or OpenAPI
Manage OAuth, API keys, connection identities, scopes, and run logs
Deploy a connector gateway locally or on self-hosted infrastructure

Supported clients

Supported clients have not been confirmed yet.