By Connectry

Where we build
what's next

Connectry Labs is the AI & MCP innovation arm of Connectry. Separate from our Salesforce AppExchange products — this is where we explore what's possible when AI meets real business workflows.

By the team behind VATCheck, LEI Lookup & Command Center
What is Labs?

The experimental
arm of Connectry

Labs is where Connectry builds AI-native tools, MCP servers, and open source utilities. These products are independent from our AppExchange line — but built with the same engineering quality and attention to detail that defines everything we ship.

Think of it as our skunkworks. We take the workflows we understand deeply — Salesforce, finance, compliance, business data — and rebuild them for the age of conversational AI.

🔬
MCP Servers
AI tools that connect real systems to AI agents. We build Model Context Protocol servers so AI agents can actually do things — not just talk about them.
Open Source
MIT licensed and community-driven. Everything we build here lives on GitHub and npm. Fork it, extend it, improve it.
🏗️
Built by Connectry
Same engineering, different playground. The team that builds Salesforce-grade software is now exploring what AI can do for real business workflows.
The Protocol Layer

Why Model Context Protocol?

MCP is the open standard that lets AI agents move from talking to doing. Here's why it changes everything for business software.

01

What is MCP?

Model Context Protocol is an open standard published by Anthropic in 2024. It defines how AI models communicate with external tools — databases, APIs, file systems, services. Think of it as USB-C for AI: a universal connector that lets any AI agent plug into any tool, anywhere, with a consistent interface.

02

Why it matters for business

Before MCP, AI assistants could only talk. They couldn't look up live data, execute trades, submit forms, or query your CRM. MCP changes that. An AI agent with MCP access can actually do things: check a customer's order, update a record, fetch real-time prices, run a compliance check — all from a single conversation.

03

How Connectry Labs builds on it

Every tool we build in Labs is an MCP server — a self-contained bridge between AI agents and a specific domain. OmniTrade bridges AI to 107+ crypto exchanges. Future tools follow the same pattern: take a domain we understand deeply, wrap it in a clean MCP interface, publish it open source. No proprietary lock-in, no black boxes.

04

What makes Labs different

Most MCP tools are built by developers learning the protocol. Connectry Labs is Salesforce-certified engineers who've spent years shipping enterprise software. That means production-grade reliability, proper error handling, security-first design, and the kind of attention to detail that comes from building AppExchange products used by businesses every day.

Connectry Labs / Products

Our Tools

Production-ready MCP servers and utilities built for the AI-native era.

Live

OmniTrade

MCP Server Open Source

Trade crypto with natural language. Connect Claude to 107+ exchanges. Portfolio management, price alerts, DCA, arbitrage detection — all by just asking.

In development

Next from Labs

Coming 2026

Something new is brewing. We're working on the next MCP server for the Labs portfolio — follow GitHub to be first to know.

In development

Next from Labs

Coming 2026

Another tool is in the works. Built with the same engineering quality as OmniTrade. Stay tuned — it's going to be worth the wait.

Frequently Asked Questions

About Connectry Labs

Common questions about Labs, MCP, and our tools.

What is Connectry Labs?

Connectry Labs is the AI & MCP innovation arm of Connectry. While our parent company builds Salesforce AppExchange products, Labs focuses on AI-native tools, MCP servers, and open source utilities that connect AI agents to real business workflows.

How is Connectry Labs related to Connectry?

Labs is a division of Connectry—same company, same engineering team, different focus. Connectry builds for Salesforce. Labs explores what's possible when AI meets real business workflows. The quality and engineering rigor is identical.

What is MCP (Model Context Protocol)?

MCP is an open standard published by Anthropic that defines how AI models communicate with external tools—databases, APIs, services. Think of it as USB-C for AI: a universal connector letting any AI agent plug into any tool with a consistent interface.

What tools does Connectry Labs build?

We build MCP servers that bridge AI agents to real-world systems. Our first product, OmniTrade, connects Claude to 107+ cryptocurrency exchanges. Future tools will follow the same pattern: take a domain we understand deeply, wrap it in a clean MCP interface.

Is OmniTrade free?

Yes. OmniTrade is open source under the MIT license. You can install it from npm (npm i -g omnitrade-mcp), use it freely, fork it, modify it, or build on top of it. No payment required, no premium tiers, no restrictions.

Are Labs products open source?

Yes. Everything we build in Labs ships open source on GitHub under the MIT license. We believe in transparent, auditable, community-driven development. Fork it, extend it, improve it—that's the point.