Build advanced AI agents with TogetherAI. Connect 600+ integrations, automate workflows, and deploy with ease using Metorial.
Learn how to securely manage your Metorial and AI SDK credentials in your applications.
Never put API keys directly in your code:
// ❌ NEVER DO THIS
const metorial = new Metorial({
apiKey: 'met_abc123xyz'
});
Instead, use environment variables:
// ✅ DO THIS
const metorial = new Metorial({
apiKey: process.env.METORIAL_API_KEY!
});
Create a .env.local
file in your project root:
# Metorial Configuration
METORIAL_API_KEY=your-metorial-api-key
METORIAL_DEPLOYMENT_ID=your-deployment-id
# AI Provider (example for OpenAI)
OPENAI_API_KEY=your-openai-api-key
Important: Add .env.local
to your .gitignore
:
# .gitignore
.env.local
.env*.local
Access them in your code:
import { Metorial } from 'metorial';
const metorial = new Metorial({
apiKey: process.env.METORIAL_API_KEY!
});
await metorial.withProviderSession(
metorialAiSdk,
{ serverDeployments: [process.env.METORIAL_DEPLOYMENT_ID!] },
async session => {
// Your code here
}
);
Consult your platform's documentation for managing environment variables:
-e
flag or docker-compose.yml
Metorial API keys should only be used server-side:
// ✅ Server-side (Next.js API Route)
export async function POST(req: Request) {
const metorial = new Metorial({
apiKey: process.env.METORIAL_API_KEY! // Safe - runs on server
});
// ...
}
// ❌ Client-side (React Component)
function MyComponent() {
const metorial = new Metorial({
apiKey: process.env.NEXT_PUBLIC_METORIAL_API_KEY // NEVER DO THIS
});
// ...
}
If you suspect a key has been compromised:
Build powerful AI applications with TogetherAI and Metorial's comprehensive integration platform. Connect TogetherAI's diverse collection of open-source language models to over 600 integrations through our MCP-powered, open-source SDKs. Metorial makes it effortless to give your TogetherAI-based agents access to calendars, databases, communication tools, project management platforms, and hundreds of other services in just a couple of lines of Python or TypeScript code. Whether you're leveraging Llama, Mistral, or other models available through TogetherAI's platform, Metorial eliminates integration complexity so you can focus on building intelligent features. Our developer-first approach handles authentication, API management, error handling, and rate limiting automatically—no more maintaining brittle integration code or debugging OAuth flows. With Metorial's open-core model, you get the transparency and flexibility of open source with the reliability and support you need for production applications. Stop wasting engineering cycles on integration plumbing and start shipping AI-powered features that differentiate your product and delight your users. Let Metorial handle the connections while you concentrate on creating breakthrough AI experiences.
Let's take your AI-powered applications to the next level, together.
Metorial provides developers with instant access to 600+ MCP servers for building AI agents that can interact with real-world tools and services. Built on MCP, Metorial simplifies agent tool integration by offering pre-configured connections to popular platforms like Google Drive, Slack, GitHub, Notion, and hundreds of other APIs. Our platform supports all major AI agent frameworks—including LangChain, AutoGen, CrewAI, and LangGraph—enabling developers to add tool calling capabilities to their agents in just a few lines of code. By eliminating the need for custom integration code, Metorial helps AI developers move from prototype to production faster while maintaining security and reliability. Whether you're building autonomous research agents, customer service bots, or workflow automation tools, Metorial's MCP server library provides the integrations you need to connect your agents to the real world.