Metorial-Node

Quick Start

This example uses Metorial Search, a built-in web search provider that requires no auth configuration. You just need two environment variables:

• METORIAL_API_KEY from platform.metorial.com
• ANTHROPIC_API_KEY from console.anthropic.com

npm install metorial @metorial/ai-sdk @ai-sdk/anthropic ai

import { anthropic } from '@ai-sdk/anthropic';
import { metorialAiSdk } from '@metorial/ai-sdk';
import { Metorial } from 'metorial';
import { stepCountIs, streamText } from 'ai';

let metorial = new Metorial({ apiKey: process.env.METORIAL_API_KEY! });

// Create a deployment for Metorial Search (built-in web search, no auth needed)
let deployment = await metorial.providerDeployments.create({
  name: 'Metorial Search',
  providerId: 'metorial-search'
});

let session = await metorial.connect({
  adapter: metorialAiSdk(),
  providers: [{ providerDeploymentId: deployment.id }]
});

let result = streamText({
  model: anthropic('claude-sonnet-4-20250514'),
  prompt:
    'Search the web for the latest news about AI agents and summarize the top 3 stories.',
  stopWhen: stepCountIs(10),
  tools: session.tools(),
  onStepFinish: step => {
    if (step.toolCalls?.length) {
      console.log(step.toolCalls.map(tc => tc.toolName).join(', '));
    }
  }
});

for await (let part of result.textStream) {
  process.stdout.write(part);
}

See the full runnable example at examples/typescript-quick-start/.

Examples

Check out the examples/ directory for more comprehensive examples:

• typescript-quick-start - Quick start with Metorial Search
• typescript-ai-sdk - AI SDK + Anthropic (v5/v6)
• typescript-ai-sdk-v4 - AI SDK + Anthropic (v4)
• typescript-anthropic - Anthropic SDK
• typescript-openai - OpenAI
• typescript-openai-compatible - Any OpenAI-compatible API
• typescript-google - Google Gemini
• typescript-deepseek - DeepSeek
• typescript-mistral - Mistral
• typescript-togetherai - TogetherAI
• typescript-xai - xAI (Grok)
• typescript-langchain - LangChain + LangGraph
• typescript-provider-config - Provider configuration patterns

LLM Integration Examples

All LLM integrations follow the same metorial.connect({ adapter, providers }) pattern. See examples/ for complete examples with every supported LLM.

Pre-Created Auth Config

An auth config represents an already-authenticated connection to a provider — for example, a user who has completed the OAuth flow for Slack. Once created (via the dashboard or a setup session), reference it by ID:

providers: [
  {
    providerDeploymentId: 'your-slack-deployment-id',
    providerAuthConfigId: 'your-auth-config-id'
  }
];

Session Options

• Streaming: Pass session.tools() into streaming APIs like AI SDK's streamText(). See the Quick Start for a full example.
• Templates: You can include { sessionTemplateId: '...' } in the providers array to load a dashboard-managed session template.
• Raw MCP access: If you need lower-level MCP session lifecycle control instead of an adapter-backed connect() session, see the lower-level SDK docs.

Metorial Node.js SDK

The official Node.js/TypeScript SDK for Metorial. Give your AI agents access to tools like Slack, GitHub, SAP, and hundreds more through MCP — without managing servers, auth flows, or infrastructure.

Sign up for a free account to get started.

Complete API Documentation

• Documentation - Documentation and guides
• API Reference - Complete API reference

Supported LLM Integrations

This SDK provides adapter packages that format MCP tools for each LLM. You can also use the API directly.