Over the last few months, I've been building a lot of AI workflows with MCPs, and I kept running ...Over the last few months, I've been building a lot of AI workflows with MCPs, and I kept running ...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Over the last few months, I've been building a lot of AI workflows with MCPs, and I kept running into the same problem.
I'd find a great SaaS product with a solid API... but no MCP.
Sometimes the team was already building one, but it had been "coming soon" for months. Other times, there were no plans to release one at all.
I didn't want to wait.
So I took the product's OpenAPI spec, generated my own MCP, and started using it.
It worked much better than I expected.
I shared it with a few people in the community, and now 5–6 other builders are using that same MCP in their own workflows.
That made me realize this isn't just my problem.
There are a lot of developers who want to use AI agents with their favorite tools today not months from now.
And there are also SaaS teams that want to offer an MCP to their users but don't want to spend months of engineering time building, testing, deploying, and maintaining another service.
So I decided to build the tool that I wish I had from day one.
🚀 Introducing 0mcp
0mcp lets you bring your own API (OpenAPI spec or API documentation), connect your API key, and generate a production-ready MCP server in minutes.
Whether you're:
a developer waiting for an official MCP,
a SaaS company looking to launch one quickly,
or a team that wants a private MCP for internal use,
0mcp helps you skip the heavy lifting and focus on building with AI.
Hi Contra, I'm Thiago, an AI engineer from Brasília, Brazil.
This is Galley Brain, the multi-agent system I run on my own VPS. Each agent owns an area (finance, schedule, operations) and takes real actions through MCP connectors, with Telegram and voice as the interface. It started as my personal assistant and is turning into a product for restaurant owners.
I build RAG systems, AI agents and n8n automations for real operations. If you're working on something similar, let's connect.
Giving each agent a clear area makes Galley Brain easier to follow as it starts taking real actions. I'd add one approval screen that shows what each agent plans before it can change money, schedules, or customer records.
I just open-sourced my Contra MCP Starter Toolkit ⚡
Contra now has a native Model Context Protocol server, which means MCP-compatible AI agents can work directly with your Contra account — profile, services, portfolio, proposals, projects, invoices and more.
The problem: getting a coding agent properly connected still involves OAuth, PKCE, token refresh, MCP configuration and making sure the agent respects Contra’s prepare → confirm workflow.
So I packaged the setup I was using into an open-source starter kit:
• One-command OAuth setup — run npm run auth, authorize Contra in the browser, and the local callback handles PKCE and token exchange.
• Zero dependencies — native Node.js 18+ only: fetch, crypto, http and fs.
• Automatic token refresh — the client catches expired sessions, refreshes the access token and retries the MCP request.
• Safe agent workflows — instructions for Cursor, Google Antigravity, Claude Code and Windsurf built around Contra’s native prepare → confirm protocol, including a full before/after review before any live mutation.
• Zero-code AI mode — copy-paste prompts for inspecting your Contra account, restructuring services, updating your profile and publishing portfolio case studies without writing JavaScript yourself.
• Content-as-Code templates — Markdown blueprints for profile positioning, flagship services, pricing, FAQs and structured case studies.
The interesting part for me isn’t just Contra.
It’s the workflow: your professional profile becomes something an AI coding agent can inspect, reason about and maintain through structured tools — while you keep final approval over every write.