How to integrate Bolna 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

Bolna logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Bolna to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Bolna agent that can list all voice agents available to me, initiate a call using your sales agent, get status of recent agent executions through natural language commands.

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

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

Also integrate Bolna with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Bolna integration
  • Using Composio's Tool Router to dynamically load and access Bolna 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 Bolna MCP server, and what's possible with it?

The Bolna MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Bolna account. It provides structured and secure access to your Bolna voice agent platform, so your agent can perform actions like listing agents, making phone calls, managing executions, and retrieving analytics on your behalf.

  • Automated voice call initiation: Let your AI agent instantly initiate phone calls using your Bolna conversational agents, streamlining outreach and support tasks.
  • Agent and phone number management: Effortlessly fetch and list all your Bolna agents or phone numbers, making it easy to review and organize your voice assets.
  • Real-time execution monitoring: Retrieve detailed information about specific call executions or monitor all executions for a given agent to track performance and outcomes.
  • Batch processing for agents: List and manage batch operations associated with your agents, supporting bulk workflows and campaign management.
  • Agent cleanup and maintenance: Quickly delete agents or batches that are no longer needed, keeping your Bolna environment organized and up to date.

Supported Tools & Triggers

Tools
Add Provider to BolnaTool to add a new telephony or voice service provider to your Bolna account.
Copy Bolna AgentTool to create a duplicate copy of an existing Bolna voice AI agent.
Create Bolna Voice AI Agent (v2)Tool to create a new Bolna Voice AI agent using the v2 API.
Create Bolna BatchTool to create a new outbound calling batch by uploading a CSV of contacts to obtain a batch_id.
Create Bolna KnowledgebaseTool to create a new knowledgebase for Voice AI agents to reference during conversations.
Create Template AgentTool to create a new Bolna Voice AI agent from a template.
Delete agent by idPermanently delete a Voice AI agent and all associated data including batches, executions, and configurations
Delete batch by idPermanently delete a batch campaign by its ID, removing it from the system.
Delete KnowledgebaseTool to permanently delete a knowledgebase from your Bolna account.
Fetch all batches by agent idRetrieve all batches associated with a specific Bolna Voice AI agent.
Get all agentsRetrieve all agents configured in your Bolna account Returns a comprehensive list of all voice agents with their configurations including: - Agent metadata (ID, name, type, status) - Task configurations (conversation settings, toolchains) - AI model settings (LLM, transcriber, synthesizer) - Webhook and phone number assignments - System prompts and guardrails This is useful for listing available agents, checking agent configurations, or finding specific agents by their properties.
Get execution by idRetrieve detailed information about a specific phone call execution by its ID.
Get knowledgebase by IDTool to retrieve details of a specific knowledgebase by its ID.
Get User InformationTool to retrieve information about the authenticated user.
Import Bolna AgentTool to import an existing Bolna voice AI agent by its ID.
List agents (paginated)Tool to retrieve a paginated list of all agents in your Bolna account.
List KnowledgebasesTool to retrieve all knowledgebases from your Bolna account.
List all phone numbersTool to list all phone numbers associated with your Bolna account.
List all providersRetrieve all providers associated with your Bolna account Returns a list of all configured providers including: - Provider IDs (unique identifiers) - Provider names (e.
List available voicesTool to list all available voices that can be utilized for Voice AI agents.
Make an outbound phone call from agentInitiate an outbound phone call using a configured Bolna Voice AI agent.
Remove Provider from Bolna AccountTool to remove a provider from your Bolna account by its key name.
Retrieve agent by idRetrieve complete configuration and details for a specific Bolna voice AI agent by its ID.
Retrieve agent execution detailsRetrieve detailed information about a specific execution (call/conversation) by an agent, including transcript, costs, duration, status, and telephony data
Retrieve agent execution statusRetrieve all executions for a specific agent with pagination and filtering support.
Retrieve Batch Details by IDRetrieve comprehensive details about a specific Bolna batch by its ID.
Retrieve batch execution listRetrieve all executions from a specific batch with pagination support.
Schedule Batch by IDSchedule a batch to execute at a specific time.
Search available phone numbersTool to search for available phone numbers that can be purchased for Bolna Voice agents.
Setup inbound call for agentAdd agent for inbound calls
Stop Agent CallsTool to stop all queued or scheduled calls for a specific Voice AI agent.
Stop batch by idStop a running batch by its ID.
Update Bolna Voice AI Agent (v2)Tool to update all settings and configuration of an existing Bolna Voice AI agent using the v2 API.

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: ["bolna"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Bolna 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 Bolna-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 Bolna 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 bolna, 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 Bolna 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 Bolna 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: ["bolna"],
  });

  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 bolna, 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 Bolna 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 Bolna MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Bolna MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Bolna MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Bolna MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Bolna MCP with Claude Cowork

Codex logo

Codex

Use Bolna MCP with Codex

OpenClaw logo

OpenClaw

Use Bolna MCP with OpenClaw

Hermes logo

Hermes

Use Bolna MCP with Hermes

CLI logo

CLI

Use Bolna MCP with CLI

Google ADK logo

Google ADK

Use Bolna MCP with Google ADK

LangChain logo

LangChain

Use Bolna MCP with LangChain

Mastra AI logo

Mastra AI

Use Bolna MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Bolna MCP with LlamaIndex

CrewAI logo

CrewAI

Use Bolna MCP with CrewAI

FAQ

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

With a standalone Bolna MCP server, the agents and LLMs can only access a fixed set of Bolna tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Bolna 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 Bolna tools.

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

Yes, absolutely. You can configure which Bolna 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 Bolna 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↗