mcp-server

Open-Connector: Connect SaaS to AI

Get a free auth gateway for startup founders to integrate 1000+ SaaS providers with AI agents.
3,243 stars252 forksTypeScriptGuide quality 8/10Updated 7/25/2026100% free · open source
What it does

Open-connector is an open-source auth gateway that connects over 1000 SaaS providers to AI agents through multiple interfaces, enabling seamless authentication and interaction.

When to use it
  • When you need to integrate multiple SaaS services with your AI application
  • When your AI agent requires secure authentication with various service providers
  • When you want to leverage a unified interface for managing connections to diverse SaaS platforms
Ready-to-paste prompt
curl -X POST 'http://localhost:3000/api/saas/connect' -H 'Content-Type: application/json' -d '{"saas": "google", "credentials": {"client_id": "your_client_id", "client_secret": "your_client_secret"}}'
Heads up: Ensure you have Node.js 16 or higher and yarn installed, as Open-connector relies on these specific versions for compatibility and performance
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/open-connector && curl -fsSL https://workflowstacks.com/api/skills/open-connector/claude-skill -o ~/.claude/skills/open-connector/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Open-Connector: Connect SaaS to AI works
Codeflow
Free to inspect

Open-Connector: Connect SaaS to AI is a very large TypeScript project (~1.1M lines across 5895 code files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~1.1M lines · 5895 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js · Docker
No API keys detected
TypeScript 100%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    package.json
    Dependencies and the commands it exposes
  4. 4
    src/server/index.ts
    Inside src/ — the main logic begins here
  5. 5
    examples/local-http/README.md
    A worked example — copy this to get going
What's in each folder
src/Core code — the actual logic5802 files
web/Frontend / UI85 files
docs/Documentation29 files
examples/Examples you can copy13 files
deploy/Deployment / infrastructure20 files
migrations/Folder15 files
scripts/Helper scripts13 files
docker/Deployment / infrastructure2 files
READMEHas testsDocumentedCI checksDocker readyExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
oomol-lab
Language
TypeScript
Category
mcp-server
Published
6/29/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.