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
This gateway aggregates or proxies other MCP servers; it only becomes useful once you connect real servers behind it.
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.
Strongest · Documentation 13/20 Weakest · Reliability 8/20
Static review · not runListed 2026-07-29
Read the FMRS scoring method →Runtime:Docker · Node.js 22+ · Hosted (no local runtime)
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.
Start the runtime with docker compose up, then connect an MCP client to http://localhost:3000/mcp and confirm connector actions appear in the tool list; alternatively run a no-auth action: curl -s -X POST http://localhost:3000/v1/actions/hackernews.get_top_stories -H 'content-type: application/' -d '{"input":{}}'.
Once connected, you can ask your AI assistant things like:
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.
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
One binary. One grammar. Evidence from the biomedical sources you already trust.
Encrypted, fully offline long-term memory for AI agents
Source revision ac0cf61313f7 Data synced 2026-10-19 Read the FMRS scoring method