How to integrate Beaconchain MCP with Vercel AI SDK v6

This guide walks you through connecting Beaconchain to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Beaconchain agent that can check if your ethereum node is syncing, get health status of the beacon chain node, fetch details for validator id 12345 through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Beaconchain account through Composio's Beaconchain MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Beaconchain logoBeaconchain
Api Key

Beaconchain is a real-time analytics platform for Ethereum 2.0's Beacon Chain. It provides detailed insights into validators, blocks, and overall network performance.

37 Tools

Introduction

This guide walks you through connecting Beaconchain to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Beaconchain agent that can check if your ethereum node is syncing, get health status of the beacon chain node, fetch details for validator id 12345 through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Beaconchain account through Composio's Beaconchain MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Beaconchain with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Beaconchain integration
  • Using Composio's Tool Router to dynamically load and access Beaconchain tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

What is the Beaconchain MCP server, and what's possible with it?

The Beaconchain MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Beaconchain account. It provides structured and secure access to Ethereum 2.0 Beacon Chain analytics, so your agent can check validator status, monitor node health, analyze network performance, and surface real-time blockchain insights on your behalf.

  • Validator information lookup: Instantly retrieve in-depth details about any specific Ethereum 2.0 validator, including performance, status, and rewards.
  • Node health monitoring: Let your agent check the real-time health status of your node, including readiness, syncing state, and error conditions.
  • Network performance insights: Surface up-to-date statistics on the overall Beacon Chain network, empowering you to make informed decisions.
  • Automated health alerts: Have your agent proactively monitor node status and notify you if any issues or anomalies arise.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management
4

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session
5

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server
6

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["beaconchain"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Beaconchain tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Beaconchain-related tools through the MCP protocol
7

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Beaconchain tools that the agent can use
8

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to beaconchain, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent
9

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Beaconchain tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Beaconchain and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["beaconchain"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to beaconchain, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Beaconchain agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.
TOOLS

Supported Tools

Every Beaconchain action and event your agent gets out of the box.

Get Chart

Retrieve chart visualizations from beaconcha.

Get Epoch

Retrieve aggregate metrics and status for a beacon chain epoch.

Get ETH1 Deposits by Transaction Hash

Retrieve all beacon chain validator deposit events associated with a specific execution-layer transaction hash.

Get ETH.Store Daily Aggregates

Retrieve ETH.

Get ERC-20 Token Balances

Retrieve a paginated list of ERC-20 token balances for a specific Ethereum address.

Get Execution Block

Retrieve one or more execution-layer blocks by block number from the Ethereum Beacon Chain.

Get Execution Produced Blocks

Retrieve execution-layer blocks attributed to one or more producers.

Get Latest State

Retrieve the latest known Ethereum Beacon Chain network state.

Get Network Performance

Retrieve aggregated network performance metrics for the Ethereum Beacon Chain.

Get Explorer Health

Check the health status of the beaconcha.

Get Validator Queues

Retrieve current queue metrics for Ethereum Beacon Chain validators.

Get Rocket Pool Validator

Retrieve Rocket Pool-specific metadata for validators including minipool status, node fee, smoothing pool status, and RPL stake metrics.

Get Slot

Retrieve detailed information about an Ethereum Beacon Chain slot.

Get Slot Attestations

Retrieve all attestations included in the beacon block for a specific slot.

Get Slot Attester Slashings

Retrieve all attester slashing operations included in the beacon block for a specific slot.

Get Slot Proposer Slashings

Retrieve all proposer slashing operations included in the beacon block for a specific slot.

Get Slot Voluntary Exits

Retrieve all voluntary exit operations included in the beacon block for a specific slot.

Get Sync Committee

Retrieve the sync committee membership for a given sync period.

Get Validator

Retrieve detailed information about an Ethereum Beacon Chain validator.

Get Validator Attestation Efficiency

Retrieve normalized attestation inclusion effectiveness for one or more validators.

Get Validator Attestations

Retrieve attestations observed for one or more validators within a bounded epoch window.

Get Validator Balance History

Retrieve per-epoch balance history for one or more Ethereum Beacon Chain validators.

Get Validator BLS Changes

Retrieve on-chain BLS-to-execution credential change messages (EIP-4881) for validators.

Get Validator Consensus Rewards

Retrieve consensus-layer rewards for one or more validators over multiple lookback windows.

Get Validator Daily Stats

Retrieve per-day statistics for a single Ethereum Beacon Chain validator by index.

Get Validator Deposits

Retrieve execution-layer deposit events for one or more validators.

Get Validator Execution Rewards

Retrieve execution-layer rewards (priority fees and MEV payments) for one or more validators.

Get Validator Income History

Retrieve a per-epoch income breakdown for one or more validators.

Get Validator Leaderboard

Retrieve the current top 100 validators ranked by 7-day consensus-layer rewards.

Get Validator Proposals

Retrieve beacon chain blocks proposed by one or more validators within a bounded epoch window.

Get Validators by Deposit Address

Retrieve validators that have made deposits from a specific execution-layer address.

Get Validators by Withdrawal Credentials

Retrieve validators whose withdrawal credentials match the provided value or execution-layer address.

Get Validators Proposal Luck

Retrieve proposal luck statistics for one or more Ethereum Beacon Chain validators.

Get Validators Queue

Retrieve current queue metrics for validators on the Ethereum Beacon Chain.

Get Validator Withdrawals

Retrieve withdrawal operations attributed to one or more validators within a bounded epoch window.

Post Validators

Retrieve validator information using a JSON request body for multiple validators.

Resolve ENS Name or Address

Resolve ENS (Ethereum Name Service) names to addresses and vice versa.

FAQ

Frequently asked questions

With a standalone Beaconchain MCP server, the agents and LLMs can only access a fixed set of Beaconchain tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Beaconchain and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Vercel AI SDK v6 fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Beaconchain tools.

Yes, absolutely. You can configure which Beaconchain scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Beaconchain data and credentials are handled as safely as possible.

Start with Beaconchain.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Beaconchain tool your agent needs.Free to start.

Start building