SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Bolna MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Bolna MCP. List all voice agents available to me, initiate a call using your sales agent, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Bolna logoBolna
Api Key

Bolna is an AI platform for building conversational voice agents. It helps businesses automate support and streamline interactions through natural, voice-powered conversations.

97 Tools

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

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

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.

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: ["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
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 Bolna 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 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
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 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.
TOOLS

Supported Tools

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

Abort workflow campaign

Move a running or paused campaign to the terminal aborted state and stop its executions.

Add custom LLM model

Register an OpenAI-compatible custom LLM endpoint with Bolna.

Add Provider to Bolna

Tool to add a new telephony or voice service provider to your Bolna account.

Add number to SIP trunk

Add a DID phone number to a SIP trunk.

Bulk create dispositions

Atomically create multiple dispositions linked to one agent.

Buy phone number

Purchase an available phone number with a recurring account charge.

Cancel workflow execution

Stop one workflow execution before its next external action.

Copy Bolna Agent

Tool 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 Batch

Tool to create a new outbound calling batch by uploading a CSV of contacts to obtain a batch_id.

Create disposition

Create a structured transcript extraction disposition linked to an agent.

Create extraction category

Create an extraction category on an agent.

Create Bolna Knowledgebase

Tool to create a new knowledgebase for Voice AI agents to reference during conversations.

Create SIP trunk

Create a bring-your-own-telephony SIP trunk.

Create sub-account

Create an enterprise sub-account with its own concurrency limits and API key.

Create workflow

Create an empty, unpublished workflow and return its identifier.

Create workflow campaign

Create a draft campaign pinned to a published workflow version.

Delete agent by id

Permanently delete a Voice AI agent and all associated data including batches, executions, and configurations

Delete batch by id

Permanently delete a batch campaign by its ID, removing it from the system.

Delete custom LLM model

Delete a custom LLM model and its stored endpoint key from Bolna.

Delete disposition

Permanently delete a disposition without changing past call results.

Delete extraction category

Permanently delete an extraction category and every disposition inside it.

Delete Knowledgebase

Tool to permanently delete a knowledgebase from your Bolna account.

Delete phone number

Permanently release a purchased phone number and stop recurring billing.

Delete SIP trunk

Permanently delete a SIP trunk and its gateways, IP identifiers, and numbers.

Delete sub-account

Permanently delete a sub-account and all of its data.

Delete workflow

Permanently delete a workflow, its draft, and all published versions.

Delete workflow campaign

Permanently delete an empty campaign only while it is draft or scheduled.

Fetch all batches by agent id

Retrieve all batches associated with a specific Bolna Voice AI agent.

Get all agents

Retrieve 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 all sub-accounts usage

Retrieve usage and cost breakdowns for every organization sub-account.

Get disposition

Retrieve one disposition, optionally requiring an agent link.

Get execution by id

Retrieve detailed information about a specific phone call execution by its ID.

Get execution raw logs

Retrieve raw transcriber, LLM, synthesizer, and telephony logs for a call.

Get knowledgebase by ID

Tool to retrieve details of a specific knowledgebase by its ID.

Get SIP trunk

Retrieve full details of one SIP trunk.

Get sub-account usage

Retrieve one sub-account's usage and cost breakdown for up to 32 days.

Get User Information

Tool to retrieve information about the authenticated user.

Get workflow

Retrieve workflow status, live settings, and version history.

Get workflow campaign

Retrieve a campaign with entry-status and validation-error counts.

Get workflow campaign entries template

Get the exact CSV header expected by a campaign's pinned workflow version.

Get workflow campaign report

Get aggregate statuses, termination reasons, and per-node funnel counts.

Get workflow draft

Retrieve a workflow's editable draft definition and revision.

Get workflow execution

Retrieve one contact's status, node attempts, state, and recent timeline.

Get workflow version

Retrieve a specific published workflow version and its full node graph.

Import Bolna Agent

Tool to import an existing Bolna voice AI agent by its ID.

List custom LLM models

List custom LLM models available in the current Bolna account scope.

List dispositions

List account-owned dispositions or dispositions linked to one agent.

List extraction categories

List an agent's extraction categories and the dispositions inside each.

List Knowledgebases

Tool to retrieve all knowledgebases from your Bolna account.

List all phone numbers

Tool to list all phone numbers associated with your Bolna account.

List all providers

Retrieve all providers associated with your Bolna account Returns a list of all configured providers including: - Provider IDs (unique identifiers) - Provider names (e.

List SIP trunks

List SIP trunks, optionally filtered by active status.

List sub-accounts

List all sub-accounts linked to the organization.

List numbers on SIP trunk

List all phone numbers assigned to a SIP trunk.

List TTS providers and models

List TTS providers and models supported for a language.

List violations

List flagged call violations, optionally filtered by status.

List available voices

List voices for one TTS provider, model, and language, with pagination.

List workflow campaign entries

List a campaign's uploaded contacts, including row validation failures.

List workflow campaign executions

List and filter the per-contact executions created by a campaign.

List workflow campaigns

List workflow campaigns with filters, sorting, and offset pagination.

List workflow node types

List workflow node types and their supported configuration fields.

List workflows

List account workflows with optional name filtering and offset pagination.

Make an outbound phone call from agent

Initiate an outbound phone call using a configured Bolna Voice AI agent.

Patch Bolna Voice AI agent (v2)

Partially update a Bolna v2 agent without replacing its full configuration.

Pause workflow campaign

Move a scheduled or running campaign to paused; only paused campaigns can be resumed, while aborted campaigns are terminal.

Publish workflow

Freeze the current valid draft as a new immutable workflow version.

Remove Provider from Bolna Account

Tool to remove a provider from your Bolna account by its key name.

Remove number from SIP trunk

Remove a phone number and any agent mapping from a SIP trunk.

Rename workflow

Rename an existing workflow.

Resend workflow execution webhook

Queue redelivery of a finished workflow execution's original webhook.

Resume workflow campaign

Move a paused campaign back to running.

Retrieve agent by id

Retrieve complete configuration and details for a specific Bolna voice AI agent by its ID.

Retrieve agent execution status

Retrieve all executions for a specific agent with pagination and filtering support.

Retrieve Batch Details by ID

Retrieve comprehensive details about a specific Bolna batch by its ID.

Retrieve batch execution list

Retrieve all executions from a specific batch with pagination support.

Run workflow

Run one contact through the workflow's latest published version.

Save workflow draft

Overwrite a workflow draft using revision-based optimistic concurrency.

Schedule Batch by ID

Schedule a batch to execute at a specific time.

Search available phone numbers

Tool to search for available phone numbers that can be purchased for Bolna Voice agents.

Setup inbound call for agent

Add agent for inbound calls

Start workflow campaign

Move a draft or scheduled campaign to running.

Stop Agent Calls

Tool to stop all queued or scheduled calls for a specific Voice AI agent.

Stop batch by id

Stop a running batch by its ID.

Stop queued or scheduled call

Cancel a queued or scheduled call before it starts.

Submit violation

Submit evidence for a Bolna violation and move it to submitted state.

Test dispositions against a transcript

Run every linked disposition against a transcript.

Test workflow webhook

Send a sample terminal execution event to a workflow's saved webhook.

Unlink inbound agent

Remove automatic inbound agent routing from a phone number.

Update Bolna Voice AI Agent (v2)

Tool to update all settings and configuration of an existing Bolna Voice AI agent using the v2 API.

Update disposition

Partially update a disposition, with optional agent-scoped copy-on-write.

Update extraction category

Rename an extraction category and/or change its extraction model.

Update SIP trunk

Partially update a SIP trunk; supplied gateway arrays replace existing arrays.

Update sub-account

Partially update an enterprise sub-account's name or concurrency limits.

Update workflow settings

Apply an RFC 7396 merge patch to a workflow's live settings.

Upload workflow campaign entries

Upload JSON contacts to a draft, scheduled, or running workflow campaign.

Validate workflow

Check a saved workflow draft for errors and warnings before publishing.

FRAMEWORKS

How to build Bolna MCP Agent with another framework

Claude Code logo

Claude Code

Use Bolna MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Bolna MCP with Claude Cowork

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

Codex logo

Codex

Use Bolna MCP with Codex

OpenClaw logo

OpenClaw

Use Bolna MCP with OpenClaw

Hermes logo

Hermes

Use Bolna MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Bolna MCP with Atomic Agent

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

Pydantic AI logo

Pydantic AI

Use Bolna MCP with Pydantic AI

AutoGen logo

AutoGen

Use Bolna MCP with AutoGen

FAQ

Frequently asked questions

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.

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.

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.

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.

Start with Bolna.It takes 30 seconds.

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

Start building