How to integrate Blazemeter MCP with Vercel AI SDK v6

This guide walks you through connecting Blazemeter to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Blazemeter agent that can start a new performance test on your main project, fetch results from the latest test run, list all test runs for project alpha through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Blazemeter account through Composio's Blazemeter MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Blazemeter logoBlazemeter
Basic

Blazemeter is a continuous testing platform for web and mobile app performance. It empowers teams to automate and analyze large-scale tests with ease.

92 Tools

Introduction

This guide walks you through connecting Blazemeter to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Blazemeter agent that can start a new performance test on your main project, fetch results from the latest test run, list all test runs for project alpha through natural language commands.

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

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

Also integrate Blazemeter with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainMastra AILlamaIndexCrewAI

TL;DR

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

The Blazemeter MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Blazemeter account. It provides structured and secure access so your agent can perform Blazemeter operations on your behalf.

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: ["blazemeter"],
  });

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

  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 blazemeter, 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 Blazemeter 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 Blazemeter action and event your agent gets out of the box.

Convert Transactions

Tool to convert transaction files to BlazeMeter DSL format for service virtualization.

Create API Monitoring Schedule

Tool to create a new schedule for running API monitoring tests.

Create Multi Test

Tool to create a new multi-test within a specified project.

Create Private Location

Tool to create a new private location in BlazeMeter.

Create Private Location Agent

Creates a new agent (server) within a BlazeMeter private location.

Create Project

Creates a new project within a BlazeMeter workspace.

Create Search

Execute a search query against BlazeMeter entities using advanced filtering and sorting.

Create Tag

Creates a new tag in BlazeMeter for organizing and categorizing resources.

Create Test

Tool to create a new single test within a specified project.

Create Workspace Asset

Tool to create an asset in a workspace for test data management.

Create Asset Dependency

Tool to create a dependency relationship between two assets in a BlazeMeter workspace.

Create Workspace Package

Creates a new package within a BlazeMeter workspace.

Create Workspace Transactions

Tool to create transactions in a BlazeMeter workspace for service virtualization.

Delete API Monitoring Schedule

Tool to delete a specific test schedule by its ID.

Delete Private Location Workspace

Tool to remove a workspace from a private location.

Delete Project

Tool to delete a specific project by its ID.

Delete Test File

Tool to delete a file from a test.

Delete Tests

Tool to delete a test by its ID.

Delete Workspace Asset Dependency

Tool to delete a dependency from a workspace's asset repository by its ID.

Delete Workspace Asset

Tool to delete an asset from a workspace in BlazeMeter's Asset Repository.

Delete Workspace Assets Dependencies

Tool to delete asset dependencies by source/target in a workspace.

Delete Workspace Logs

Tool to delete master test execution logs from a BlazeMeter workspace.

Delete Workspace Managers

Tool to remove managers from a workspace.

Delete Workspace Package

Tool to delete a package from a workspace in the BlazeMeter Asset Repository.

Duplicate Test

Tool to duplicate an existing test by its ID.

Export Package

Tool to export a package from BlazeMeter Asset Repository as a zip file.

Export Workspaces Packages

Tool to export multiple packages from a workspace as a zip file.

Generate Test Data from Data Model

Tool to generate test data from a data model in Asset Repository.

Generate Workspace Test Data

Tool to generate synthetic test data on-the-fly without storing in Asset Repository.

Get Accounts

Tool to retrieve a list of accounts associated with the authenticated user.

Get API Monitoring Schedule

Tool to retrieve details of a specific API monitoring schedule by its ID.

Get API Monitoring Schedules

Retrieves a paginated list of API monitoring test schedules.

Get Generator Functions

Tool to retrieve all available test data generator functions from BlazeMeter Test Data API.

Get Generator Seed Lists

Tool to retrieve a list of all available seed lists from BlazeMeter Test Data Management API.

Get Info Health

Tool to retrieve the BlazeMeter service health status.

Get Info Version

Tool to retrieve BlazeMeter service version information.

Get Masters Reports Main Summary

Tool to retrieve request statistics summary for a master test run.

Get Multi Test

Tool to retrieve details of a specific multi-test.

Get Multi Tests

Retrieves a paginated list of multi-tests within a BlazeMeter workspace.

Get Private Locations

Tool to retrieve a list of private locations filtered by account or workspace.

Get Project Details

Tool to retrieve detailed information about a specific project by its ID.

Get Projects

Tool to retrieve a list of projects within a specified workspace.

Get Regions

Tool to retrieve a list of all available test regions for API monitoring.

Get Search Metadata

Retrieve metadata about searchable entities, fields, relationships, and operators in BlazeMeter's search API.

Get Shared Folders

Tool to retrieve a list of shared folders within a specified workspace.

Get Tags

Tool to retrieve a list of all tags from BlazeMeter Mock Services API.

Get Test Details

Tool to retrieve complete details of a specific test by its ID.

Get Tests

Retrieve a list of performance tests filtered by workspace or project.

Get Tests Files

Tool to list all files associated with a test.

Get Test Validations

Tool to retrieve validation results for a specific test by its ID.

Get User

Retrieve the authenticated user's profile information including their default project and preferences.

Get User Active Sessions

Tool to retrieve the list of active test sessions for the authenticated user.

Get User Invites

Tool to retrieve pending invites for the authenticated user.

Get User Projects

Tool to retrieve all projects belonging to the authenticated user.

Get Workspace Details

Tool to retrieve detailed information about a specific workspace by its ID.

Get Workspace Package

Tool to retrieve a specific package by its ID from a workspace in the BlazeMeter Asset Repository.

Get Workspaces

Tool to retrieve a list of workspaces for a specified account.

Get Workspace Assets

Tool to retrieve all data models (assets) in a workspace for Test Data Management.

Get Workspace Asset By ID

Tool to retrieve a specific asset by ID from the Test Data Management Asset Repository.

Get Workspace Asset Data

Tool to retrieve data from a specific asset in a workspace's asset repository.

Get Workspace Assets Dependencies

Tool to retrieve all dependencies for a given workspace with optional filtering criteria.

Get Workspace Asset Dependency

Tool to retrieve a specific dependency by ID from a workspace's asset repository.

Get Asset Dependencies

Tool to retrieve dependencies for a specific asset in a workspace from the BlazeMeter Asset Repository.

Get Workspace Data Model By ID

Tool to retrieve a specific data model by ID from a workspace in Test Data Management.

Get Virtual Service Template by ID

Tool to get virtual service template details from a specific workspace.

Get Workspace Packages

Tool to retrieve packages from a BlazeMeter workspace.

Get Workspace Package Dependencies

Tool to retrieve package dependencies for a specific package in a workspace.

Get Workspace Service Mock Templates

Tool to list virtual service templates available in a workspace.

Get Workspace Transactions

Tool to list transactions for virtual services in a workspace.

Get Workspace Users

Tool to retrieve a list of users within a specified workspace.

Import Workspace Package

Import a package from a ZIP file into a BlazeMeter workspace.

List Generator Card Issuers

Tool to retrieve a list of available card issuers for test data generation.

Publish API Data

Publishes test data through the BlazeMeter Test Data Management API.

Register User

Tool to register a new user account in BlazeMeter.

Start Test

Tool to start a preconfigured performance load test.

Stop Master

Gracefully stop a running BlazeMeter test execution (master) by its ID.

Stop Test

Tool to stop all active masters (test executions) for a given test ID.

Terminate User Active Sessions

Tool to immediately terminate active user sessions in BlazeMeter.

Terminate Workspaces Masters

Tool to terminate all running masters in a BlazeMeter workspace.

Update API Monitoring Schedule

Tool to update the configuration of an existing API monitoring schedule.

Update Project

Tool to update an existing BlazeMeter project by its ID.

Update Test

Tool to update details of a specific test by its ID.

Update Workspace Asset

Tool to update an existing asset in a BlazeMeter workspace.

Update Workspaces Assets Dependencies

Tool to update asset dependencies in a BlazeMeter workspace.

Update Workspace Package

Tool to update an existing package in a BlazeMeter workspace.

Update Workspace Package Dependencies

Tool to update package dependencies for a specific package in a workspace.

Update Workspace Service Mock Template

Tool to update a virtual service template configuration (Service Virtualization).

Update Workspace User

Tool to update a user's role and status within a BlazeMeter workspace.

Upload Test Files

Upload a file asset (script, data file, or configuration) to a BlazeMeter test.

Upload Workspace Asset Data

Tool to upload asset data to a BlazeMeter workspace.

Validate Test

Tool to validate a specific test by its ID.

Validate Workspace Asset

Tool to validate a data model asset in a workspace for test data management.

FRAMEWORKS

How to build Blazemeter MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Blazemeter MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Blazemeter MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Blazemeter MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Blazemeter MCP with Claude Cowork

Codex logo

Codex

Use Blazemeter MCP with Codex

OpenClaw logo

OpenClaw

Use Blazemeter MCP with OpenClaw

Hermes logo

Hermes

Use Blazemeter MCP with Hermes

CLI logo

CLI

Use Blazemeter MCP with CLI

Google ADK logo

Google ADK

Use Blazemeter MCP with Google ADK

LangChain logo

LangChain

Use Blazemeter MCP with LangChain

Mastra AI logo

Mastra AI

Use Blazemeter MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Blazemeter MCP with LlamaIndex

CrewAI logo

CrewAI

Use Blazemeter MCP with CrewAI

FAQ

Frequently asked questions

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

Yes, absolutely. You can configure which Blazemeter 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 Blazemeter data and credentials are handled as safely as possible.

Start with Blazemeter.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies