How to integrate Bamboohr MCP with Autogen

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

30 min · no commitment · see it on your stack

Bamboohr logo
AutoGen logo
divider

Introduction

This guide walks you through connecting Bamboohr to AutoGen using the Composio tool router. By the end, you'll have a working Bamboohr agent that can add new dependent for employee john doe, update direct deposit details for sarah smith, log overtime hours for marketing team members through natural language commands.

This guide will help you understand how to give your AutoGen 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.

Also integrate Bamboohr with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Bamboohr
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Bamboohr tools
  • Run a live chat loop where you ask the agent to perform Bamboohr operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

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 your HR data, so your agent can perform actions like managing employee benefits, updating payroll records, tracking time, and assisting with applicant management on your behalf.

  • Employee benefits administration: Automatically enroll employees in benefit groups, create or update benefit records, and manage company-wide benefit offerings with ease.
  • Payroll and direct deposit management: Enable your agent to create paystubs, add unpaid pay periods, and update employee direct deposit information for seamless payroll processing.
  • Dependent and tax record updates: Empower your agent to add employee dependents and modify withholding details, keeping employee records accurate and compliant.
  • Time tracking automation: Let your agent log new time tracking records for employees, ensuring precise attendance and overtime data for reporting and payroll.
  • Applicant and recruitment collaboration: Allow your agent to post comments on applicant records, streamlining feedback and communication during the hiring process.

Supported Tools & Triggers

Tools
Create Candidate ApplicationTool to create a candidate application.
Create Job OpeningTool to create a new job opening in BambooHR ATS.
List Job ApplicationsTool to list job applications with optional filters.
Get Benefit CoveragesTool to retrieve standard benefit coverage options.
Get Member Benefit EventsTool to list member benefit events.
Get Company EINsTool to retrieve company Employer Identification Numbers (EINs).
Get Company InformationTool to retrieve company information.
Create File CategoryTool to create new company file categories.
Create Time Off RequestTool to submit a new time off request.
List DatasetsTool to list available datasets via the Datasets API.
Create Employee DependentTool to add a dependent to an employee.
Get All Employee DependentsTool to retrieve all employee dependents.
Create EmployeeTool to create a new employee record.
Create Employee File CategoryTool to create new employee file categories.
Get Changed EmployeesTool to get employees inserted, updated, or deleted since a given timestamp.
List Company FilesTool to list company file categories and their files.
Upload Company FileTool to upload a new company file.
Get All EmployeesRetrieves all employees from the BambooHR employee directory including their basic information and status.
Get Applicant StatusesTool to retrieve applicant statuses.
Get Custom Employee FieldsTool to fetch custom employee field values.
Run Custom ReportTool to run a custom report by ID or ad-hoc fields.
Get EmployeeTool to retrieve detailed information for a specific employee.
Get Employee PhotoTool to retrieve an employee's profile photo by size.
Get Hiring LeadsTool to retrieve potential hiring leads (employees who can manage job openings) for use in creating a new job opening.
Get Job SummariesTool to retrieve a list of ATS job summaries.
Get Departments MetadataTool to list department metadata.
Get Meta DivisionsTool to list all division metadata.
List Employment Status MetadataTool to list all employment status metadata.
Get Meta Job TitlesTool to retrieve job title metadata.
Get Meta LocationsTool to list location metadata.
Get Time-Off Types MetadataTool to list time-off type metadata.
Get ReportTool to fetch a built-in or published report in JSON or other formats.
Get Time-Off BalancesTool to retrieve time-off balances for employees.
Get Time-Off RequestsTool to list time-off requests within a date range.
List Company ReportsTool to list all available company and custom reports.
Get Country OptionsTool to retrieve all available country options.
Get List Field DetailsTool to get details for all list fields.
Get Tabular Fields MetadataTool to list tabular table fields metadata.
Get UsersTool to list active users with basic info.
Update EmployeeTool to update fields on a specified employee record.
Update Time Off RequestTool to update the status of an existing time-off request.

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

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Bamboohr account you can connect to Composio
  • Some basic familiarity with Autogen and Python async

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 dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Bamboohr via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Bamboohr connections to use

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Bamboohr session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["bamboohr"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Bamboohr tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Bamboohr assistant agent with MCP tools
    agent = AssistantAgent(
        name="bamboohr_assistant",
        description="An AI assistant that helps with Bamboohr operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Bamboohr tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Bamboohr related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Bamboohr tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Bamboohr and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Bamboohr session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["bamboohr"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Bamboohr assistant agent with MCP tools
        agent = AssistantAgent(
            name="bamboohr_assistant",
            description="An AI assistant that helps with Bamboohr operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Bamboohr related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Bamboohr through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Bamboohr, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Bamboohr MCP Agent with another framework

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

Claude Code logo

Claude Code

Use Bamboohr MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Bamboohr MCP with Claude Cowork

Codex logo

Codex

Use Bamboohr MCP with Codex

OpenClaw logo

OpenClaw

Use Bamboohr MCP with OpenClaw

Hermes logo

Hermes

Use Bamboohr MCP with Hermes

CLI logo

CLI

Use Bamboohr MCP with CLI

Google ADK logo

Google ADK

Use Bamboohr MCP with Google ADK

LangChain logo

LangChain

Use Bamboohr MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Bamboohr MCP with Vercel AI SDK

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

FAQ

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

With a standalone Bamboohr MCP server, the agents and LLMs can only access a fixed set of Bamboohr tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Bamboohr and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Autogen?

Yes, you can. Autogen 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 Bamboohr tools.

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

Yes, absolutely. You can configure which Bamboohr 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 Bamboohr 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↗
Bamboohr MCP Integration with AutoGen | Composio