How to integrate Beaconchain MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Beaconchain logo
Vercel AI SDK logo
divider

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.

Supported Tools & Triggers

Tools
Get ChartRetrieve chart visualizations from beaconcha.
Get EpochRetrieve aggregate metrics and status for a beacon chain epoch.
Get ETH1 Deposits by Transaction HashRetrieve all beacon chain validator deposit events associated with a specific execution-layer transaction hash.
Get ETH.Store Daily AggregatesRetrieve ETH.
Get ERC-20 Token BalancesRetrieve a paginated list of ERC-20 token balances for a specific Ethereum address.
Get Execution BlockRetrieve one or more execution-layer blocks by block number from the Ethereum Beacon Chain.
Get Execution Produced BlocksRetrieve execution-layer blocks attributed to one or more producers.
Get Latest StateRetrieve the latest known Ethereum Beacon Chain network state.
Get Network PerformanceRetrieve aggregated network performance metrics for the Ethereum Beacon Chain.
Get Explorer HealthCheck the health status of the beaconcha.
Get Validator QueuesRetrieve current queue metrics for Ethereum Beacon Chain validators.
Get Rocket Pool ValidatorRetrieve Rocket Pool-specific metadata for validators including minipool status, node fee, smoothing pool status, and RPL stake metrics.
Get SlotRetrieve detailed information about an Ethereum Beacon Chain slot.
Get Slot AttestationsRetrieve all attestations included in the beacon block for a specific slot.
Get Slot Attester SlashingsRetrieve all attester slashing operations included in the beacon block for a specific slot.
Get Slot Proposer SlashingsRetrieve all proposer slashing operations included in the beacon block for a specific slot.
Get Slot Voluntary ExitsRetrieve all voluntary exit operations included in the beacon block for a specific slot.
Get Sync CommitteeRetrieve the sync committee membership for a given sync period.
Get ValidatorRetrieve detailed information about an Ethereum Beacon Chain validator.
Get Validator Attestation EfficiencyRetrieve normalized attestation inclusion effectiveness for one or more validators.
Get Validator AttestationsRetrieve attestations observed for one or more validators within a bounded epoch window.
Get Validator Balance HistoryRetrieve per-epoch balance history for one or more Ethereum Beacon Chain validators.
Get Validator BLS ChangesRetrieve on-chain BLS-to-execution credential change messages (EIP-4881) for validators.
Get Validator Consensus RewardsRetrieve consensus-layer rewards for one or more validators over multiple lookback windows.
Get Validator Daily StatsRetrieve per-day statistics for a single Ethereum Beacon Chain validator by index.
Get Validator DepositsRetrieve execution-layer deposit events for one or more validators.
Get Validator Execution RewardsRetrieve execution-layer rewards (priority fees and MEV payments) for one or more validators.
Get Validator Income HistoryRetrieve a per-epoch income breakdown for one or more validators.
Get Validator LeaderboardRetrieve the current top 100 validators ranked by 7-day consensus-layer rewards.
Get Validator ProposalsRetrieve beacon chain blocks proposed by one or more validators within a bounded epoch window.
Get Validators by Deposit AddressRetrieve validators that have made deposits from a specific execution-layer address.
Get Validators by Withdrawal CredentialsRetrieve validators whose withdrawal credentials match the provided value or execution-layer address.
Get Validators Proposal LuckRetrieve proposal luck statistics for one or more Ethereum Beacon Chain validators.
Get Validators QueueRetrieve current queue metrics for validators on the Ethereum Beacon Chain.
Get Validator WithdrawalsRetrieve withdrawal operations attributed to one or more validators within a bounded epoch window.
Post ValidatorsRetrieve validator information using a JSON request body for multiple validators.
Resolve ENS Name or AddressResolve ENS (Ethereum Name Service) names to addresses and vice versa.

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

Prerequisites

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

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.

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

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

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

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

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

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

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.

How to build Beaconchain MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Beaconchain MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Beaconchain MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Beaconchain MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Beaconchain MCP with Claude Cowork

Codex logo

Codex

Use Beaconchain MCP with Codex

OpenClaw logo

OpenClaw

Use Beaconchain MCP with OpenClaw

Hermes logo

Hermes

Use Beaconchain MCP with Hermes

CLI logo

CLI

Use Beaconchain MCP with CLI

Google ADK logo

Google ADK

Use Beaconchain MCP with Google ADK

LangChain logo

LangChain

Use Beaconchain MCP with LangChain

Mastra AI logo

Mastra AI

Use Beaconchain MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Beaconchain MCP with LlamaIndex

CrewAI logo

CrewAI

Use Beaconchain MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Beaconchain MCP?

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.

Can I use Tool Router MCP with Vercel AI SDK v6?

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.

Can I manage the permissions and scopes for Beaconchain while using Tool Router?

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.

How safe is my data with Composio Tool Router?

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.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for freeGet a demo↗