SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Bamboohr MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Bamboohr MCP. Add new dependent for employee john doe, update employee details for sarah smith, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Bamboohr logoBamboohr
Oauth2Api Key

BambooHR is a cloud-based HR management platform for small and mid-sized businesses. It streamlines employee data, HR workflows, and reporting in one easy interface.

42 Tools

Introduction

This guide walks you through connecting Bamboohr to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Bamboohr agent that can look up and update employees, manage time off requests, create job openings, track applications, and run custom reports through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Bamboohr with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKMuseCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

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

The BambooHR MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your BambooHR account. It provides structured and secure access to employee records, hiring data, time off, benefits, reports, and company files, so your agent can manage employees, track candidates, submit time off requests, run reports, and organize HR documents on your behalf.

  • Employee records and organization: Have your agent retrieve or create employee records, find recent employee changes, and review departments, divisions, locations, job titles, and employment statuses.
  • Hiring and candidate management: Direct your agent to create job openings and candidate applications, list applications, check applicant statuses, and review hiring leads or job summaries.
  • Time off administration: Let the agent submit time off requests, review requests within a date range, check employee balances, and inspect available time off types and policies.
  • Reports, benefits, and company data: Instruct your agent to run company reports, review benefit coverages and member events, or retrieve company information and tax identifiers.
  • HR files and employee details: Have your agent list or upload company files, create file categories, retrieve employee photos and custom fields, or add and review employee dependents.

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: ["bamboohr"],
  });

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

  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 bamboohr, 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 Bamboohr 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 Bamboohr action and event your agent gets out of the box.

Create Candidate Application

Tool to create a candidate application.

Create Job Opening

Tool to create a new job opening in BambooHR ATS.

List Job Applications

Tool to list job applications with optional filters.

Get Benefit Coverages

Tool to retrieve standard benefit coverage options.

Get Member Benefit Events

Lists member benefit enrollment events for employees and their dependents over the past year, with optional offset and limit on returned members.

Get Company EINs

Tool to retrieve company Employer Identification Numbers (EINs).

Get Company Information

Tool to retrieve company information.

Create File Category

Tool to create new company file categories.

Create Time Off Request

Tool to submit a new time off request.

List Datasets

Lists available datasets via the BambooHR Datasets API, returning dataset names and labels for discovery before querying.

Create Employee Dependent

Tool to add a dependent to an employee.

Get All Employee Dependents

Tool to retrieve all employee dependents.

Create Employee

Tool to create a new employee record.

Create Employee File Category

Tool to create new employee file categories.

Get Changed Employees

Get employee IDs grouped by inserted, updated, or deleted changes since a given timestamp.

List Company Files

List company file categories and their files that the requesting user is permitted to see.

Upload Company File

Tool to upload a new company file.

Get All Employees

Retrieves all employees from the BambooHR employee directory including their basic information and status.

Get Applicant Statuses

Tool to retrieve applicant statuses.

Get Custom Employee Fields

Lists employee field definitions available in the account, including standard and custom fields.

Run Custom Report

Tool to run a custom report by ID or ad-hoc fields.

Get Employee

Tool to retrieve detailed information for a specific employee.

Get Employee Photo

Retrieve an employee's profile photo by ID and size, returning its content as Base64 with a filename and MIME type.

Get Hiring Leads

Tool to retrieve potential hiring leads (employees who can manage job openings) for use in creating a new job opening.

Get Job Summaries

Retrieve ATS job opening summaries, optionally filtered by status group and sorted.

Get Departments Metadata

Tool to list department metadata.

Get Meta Divisions

Tool to list all division metadata.

List Employment Status Metadata

Tool to list all employment status metadata.

Get Meta Job Titles

Tool to retrieve job title metadata.

Get Meta Locations

Tool to list location metadata.

Get Time-Off Types Metadata

Tool to list time-off type metadata.

Get Report

Tool to fetch a built-in or published report in JSON or other formats.

Get Time-Off Balances

Retrieve estimated time-off balances for specified employees as of an optional end date.

Get Time-Off Policies

List time-off policies, with accrual and rollover details when available.

Get Time-Off Requests

Tool to list time-off requests within a date range.

List Company Reports

Lists a page of saved custom reports available in the account.

Get Country Options

Retrieve BambooHR country options for use when updating or validating country fields.

Get List Field Details

Tool to get details for all list fields.

Get Tabular Fields Metadata

Tool to list tabular table fields metadata.

Get Users

List company users with basic information, including IDs, names, email addresses, and account status.

Update Employee

Tool to update fields on a specified employee record.

Update Time Off Request

Tool to update the status of an existing time-off request.

FRAMEWORKS

How to build Bamboohr MCP Agent with another framework

Claude Code logo

Claude Code

Use Bamboohr MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Bamboohr MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Bamboohr MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Bamboohr MCP with Claude Agent SDK

Muse logo

Muse

Use Bamboohr MCP with Muse

Codex logo

Codex

Use Bamboohr MCP with Codex

OpenClaw logo

OpenClaw

Use Bamboohr MCP with OpenClaw

Hermes logo

Hermes

Use Bamboohr MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Bamboohr MCP with Atomic Agent

Google ADK logo

Google ADK

Use Bamboohr MCP with Google ADK

LangChain logo

LangChain

Use Bamboohr MCP with LangChain

Mastra AI logo

Mastra AI

Use Bamboohr MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Bamboohr MCP with LlamaIndex

CrewAI logo

CrewAI

Use Bamboohr MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Bamboohr MCP with Pydantic AI

AutoGen logo

AutoGen

Use Bamboohr MCP with AutoGen

FAQ

Frequently asked questions

Start with Bamboohr.It takes 30 seconds.

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

Start building