Sign in Book a demo
Back to Tools
Productivity & Docs OAuth
Build Your Agent View Workday Documentation
workday logo

Workday MCP Tools for AI Agents

Let an agent check time-off balances, review request status and history, validate dates, and prepare a time-off request for the signed-in worker.

Available Tools

10 tools available in this integration

Workday.CreateTimeOffRequest

Request time off for the signed-in worker, asking for a draft by default.

Workday.ListEligibleTimeOffTypes

List the time-off types the signed-in worker can request, with their rules.

Workday.ListTimeOffBalances

Show how much time off the signed-in worker has left, by plan.

Workday.ListTimeOffHistory

Browse the time off the signed-in worker has already logged.

Workday.ListTimeOffRequests

List the signed-in worker's time-off requests and where each one stands.

Workday.ListTimeOffStatus

Show where the signed-in worker's time-off requests stand right now.

Workday.ListValidTimeOffDates

Check whether Workday accepts each date for the selected time-off type.

Workday.RequestTimeOff

Request time off for the signed-in worker, asking for a draft by default.

Workday.ValidateTimeOffDates

Check whether Workday accepts each date for the selected time-off type.

Workday.WhoAmI

Identify the Workday worker the connection is signed in as, and their jobs.

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "check whether I have enough vacation time for these dates and prepare the request." Arcade picks the right Workday actions without guessing the worker or time-off type first.

Up to 100x fewer tokens

Workday time-off reads return focused balances, dates, histories, and request statuses, so the agent can decide what to do without loading unrelated worker or payroll data into the model.

Complete the workflow end to end

Identify the worker, check eligible time-off types and balances, validate the dates, prepare the request, and check its status through one toolkit designed around the complete time-off task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing Workday

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For Workday, you can implement some of these policies:

Access when tools are listed for a user
  • Hide Workday.RequestTimeOff from agents unless the roles your IDP marks as employees authorized to submit their own time-off requests are active, so an agent cannot request leave for an unauthorized worker.
  • Hide Workday.CreateTimeOffRequest from agents unless the roles your IDP marks as employees authorized to submit their own leave requests are active, so an agent cannot create a request for an unauthorized worker.
Pre-execution before each tool call
  • Require human approval before Workday.RequestTimeOff runs, so an agent cannot submit time off without the worker's confirmation.
  • Require human approval before Workday.CreateTimeOffRequest runs, so an agent cannot submit a leave request without the worker's confirmation.
Post-execution after the tool returns
  • Redact Workday.ListTimeOffBalances results for plans containing compensation, payroll, or other restricted balance details before they reach the model.
  • Strip personal notes, medical details, and other sensitive explanations from Workday.ListTimeOffHistory results before the model sees them.
  • Redact job titles, positions, and other employment details from Workday.WhoAmI results unless the agent's task requires them.
  • Strip manager names, approver identities, and private comments from Workday.ListTimeOffRequests results before they reach the model, so the agent sees request status without exposing other workers' details.
  • Redact internal scheduling rules and exception explanations from Workday.ValidateTimeOffDates results before the model sees them, so date validation does not reveal workforce-planning details.

How to use Workday with your agent

Connect Workday to an MCP client and let each worker authorize their own account. Follow the setup from connection through your first time-off workflow.

Your questions, answered

A Workday MCP server exposes Workday capabilities as structured tools that an AI agent can call through the Model Context Protocol. After a worker authorizes their account, the agent can check time-off information, validate dates, and submit permitted requests.

Arcade provides Workday MCP access through an integration built by Arcade, with per-user OAuth and an actions runtime for approval, redaction, and access controls. This gives teams one governed way to connect Workday from supported agents and clients.

Arcade agents can identify the signed-in worker, list eligible time-off types, check balances and history, review existing request status, validate dates, and create time-off requests as drafts by default.

Each worker authorizes their own Workday account with the permissions needed for the enabled actions. Read workflows need access to the worker's identity and time-off data; submitting a request also requires permission to create time-off requests, with exact access controlled by the Workday tenant.

Yes. Each user authorizes their own Workday account through OAuth. Actions run under that user's authorization, so the agent can access only the worker and permissions that person has approved.

Yes. Contextual Access policies can require human approval before a time-off request is submitted. The call proceeds only after the policy's conditions have been satisfied.

Arcade proxies Workday API calls and does not persist your content as part of normal tool execution. Credentials are brokered and stored encrypted at rest, and the model never receives them.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade refreshes access while the user's Workday authorization remains valid. If it is revoked, rotated, or can no longer be refreshed, calls stop until the worker reconnects their Workday account.

Workday tenant and API rate limits apply to calls made through Arcade. The Workday integration does not remove those limits, so agents should avoid repeatedly fetching the same balances, history, or request status.

Ready to actually ship your agent?

Connect your agent to Workday with managed OAuth, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the Workday Quickstart