How to integrate Workday MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Workday Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Workday to AutoGen using the Composio tool router. By the end, you'll have a working Workday agent that can request vacation days for next week, check my current absence balance, find all open job postings i manage, summarize feedback from recent interviews through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Workday account through Composio's Workday MCP server.

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

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 Workday
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Workday tools
  • Run a live chat loop where you ask the agent to perform Workday 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 Workday MCP server, and what's possible with it?

The Workday MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Workday account. It provides structured and secure access to your HR, payroll, and recruiting data, so your agent can perform actions like managing time off, retrieving employee details, tracking job postings, and analyzing interview feedback on your behalf.

  • Automated time off management: Easily create new time off requests or check absence balances for yourself or others, making leave management effortless.
  • Employee data and profile retrieval: Have your agent fetch profile details for the current user or any specified worker to simplify onboarding and HR processes.
  • Comprehensive job posting insights: Instantly retrieve information about job postings, including descriptions and screening questionnaires, to aid recruiters and hiring managers.
  • Interview feedback analysis: Let your agent pull and summarize interview feedback entries to streamline debriefs and improve hiring decisions.
  • Access to holiday and leave events: Quickly get holiday schedules and leave status values for better workforce planning and scheduling.

Supported Tools & Triggers

Tools
Create Time Off RequestCreates a time off request for the specified worker id and initiates the business process.
Get Absence BalanceRetrieves the specified balance of all absence plan and leave of absence types.
Get Balance DetailsRetrieves the specified balance of all absence plan and leave of absence types.
Get Current UserRetrieves the current authenticated worker's profile information from workday.
Get Holiday EventsReturns the holiday events for the specified workers and time period.
Get Interview FeedbackRetrieves feedback entries for a specific interview to prepare debrief notes with highlights and lowlights.
Get Job PostingRetrieves detailed information about a specific job posting including job description.
Get Job Posting QuestionnaireRetrieves screening questions and questionnaires associated with a specific job posting.
Get Leave Status ValuesRetrieves instances that can be used as values for other endpoint parameters in this service.
Get My Job PostingsFinds all job postings assigned to a specific recruiter by analyzing interviews and job requisitions.
Get ProspectRetrieves a single prospect instance for talent matching and best-fit analysis.
Get Prospect EducationsRetrieves the education of a prospect for talent matching and best-fit analysis.
Get Prospect ExperiencesRetrieves the work experience of a prospect for talent matching and best-fit analysis.
Get Prospect Resume AttachmentsRetrieves resume attachments for a specific prospect to help prepare for upcoming interviews.
Get Prospect SkillsRetrieves the skills of a prospect for talent matching and best-fit analysis.
Get Time Off Status ValuesRetrieves instances that can be used as values for other endpoint parameters in this service.
Get Worker Eligible Absence TypesRetrieves a collection of eligible absence types for the specified worker.
Get Worker Leaves of AbsenceRetrieves the leaves of absence for the specified worker using the working absencemanagement v1 api.
Get Worker Time Off DetailsRetrieves a collection of time off details for the specified worker.
Get Worker Valid Time Off DatesRetrieves the valid time off dates for the specified worker id for the given dates.
List Absence BalancesRetrieves the balance of all absence plan and leave of absence type for the specified worker id.
List BalancesRetrieves the balance of all absence plan and leave of absence type for the specified worker id.
List InterviewsRetrieves a list of interviews with job requisition and recruiter assignment details.
List Job PostingsRetrieves a list of job postings from workday recruiting system with filtering options.
List WorkersRetrieves a collection of workers and current staffing information.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router 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 Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router 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 Workday 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 Workday 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 Workday 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 Workday session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["workday"]
    )
    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 Workday 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 Workday assistant agent with MCP tools
    agent = AssistantAgent(
        name="workday_assistant",
        description="An AI assistant that helps with Workday 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 Workday 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 Workday 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 Workday 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 Workday 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 Workday session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["workday"]
    )
    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 Workday assistant agent with MCP tools
        agent = AssistantAgent(
            name="workday_assistant",
            description="An AI assistant that helps with Workday 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 Workday 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 Workday 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 Workday, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Workday MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Workday MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Workday MCP with Claude Agent SDK

Google ADK

Google ADK

Use Workday MCP with Google ADK

LangChain

LangChain

Use Workday MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Workday MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Workday MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Workday MCP with LlamaIndex

CrewAI

CrewAI

Use Workday MCP with CrewAI

FAQ

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

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

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

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

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
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.

Book a call↗Get started for free