LangChain Announces Open Agent Platform Powered by Arcade.dev

Sam Partee

MAY 14, 2025

1 MIN READ

PRODUCT RELEASE

At the Interrupt Conference, LangChain unveiled a new agent platform that allows developers to build and share AI agents. The platform leverages Arcade.dev's support for Model Context Protocol (MCP) to enable agents to perform actions on behalf of users across hundreds of services.

Why This Matters:

Complete Agent Ecosystem: Developers can now build, share, and deploy AI agents through an intuitive platform with flexible hosting options
Powerful Action Capabilities: Thanks to Arcade.dev, agents can securely interact with hundreds of services including Google, Slack, Stripe, and Salesforce
Open Standards Support: Full compatibility with MCP ensures interoperability with any MCP server that supports HTTPS, creating an extensible foundation for agent development

How It Works:

The LangChain agent platform provides a versatile environment with streamlined agent creation and management through a new UI. Developers can choose between LangGraph cloud hosting or local development using LangGraph Studio.

By leveraging Arcade.dev's extensive library of integrations and first-class MCP support, the platform enables agents to securely interact with hundreds of external services while maintaining proper permissions.

Open Agent Platform ──▶ MCP Server (Arcade.dev) ──▶ 🔗 Connected Tools

Ongoing Collaboration:

Arcade and LangChain continue to work together to enhance the platform and advance community standards like MCP, ensuring the best possible experience for agent developers.

Availability:

If you're building an agent yourself, sign up today to use Arcade.dev's integration library!

If you're building on MCP, join the beta waitlist for our MCP gateway (which powers LangChain Open Agent Platform).

SHARE THIS POST

RECENT ARTICLES

OCTOBER 6, 2025

THOUGHT LEADERSHIP

AgentKit Ships, But Production Agents Still Need Authentication

OpenAI just dropped AgentKit at DevDay, and the demos look clean—visual workflow builders, embedded chat interfaces, evaluation frameworks. Ramp went from blank canvas to live buyer agent in hours instead of months. LY Corporation built a multi-agent workflow in under two hours. But here's what the launch post doesn't tell you: most of those demos will hit a wall before production. What AgentKit Actually Shipped AgentKit is three things bundled together: Agent Builder gives you a visual can

SEPTEMBER 26, 2025

THOUGHT LEADERSHIP

Agent Auth: The Problem That Kills Production Agents

Your agent needs to pull data from Google Drive, post a summary to Slack, and create a Jira ticket. Simple request. But whose credentials does it use? Should it have permission to delete your entire Drive folder? This authorization problem kills agent demos before they reach production. It's not about users logging into your agent (LangGraph Platform handles that). It's about your agent accessing other services on behalf of those users. If you're building real agents, you've hit this wall. The

SEPTEMBER 16, 2025

PRODUCT RELEASE

Your AI Agent Doesn't Know Who the Hell You Are (And That's a Problem)

Picture this: You walk into a newly opened restaurant for the first time, excited by the positive reviews, and confidently stride to a window-side table. As soon as you're settled, the waiter approaches, but before they can speak, you say, "The usual, please." The waiter stares at you like you've lost your mind. They've never seen you before. They have no idea what "the usual" means. That's your AI agent every time you start a new conversation. It has absolutely no idea who you are, what you w

Get early access to Arcade, and start building now.

Docs