Workable for AI agents

Workable is hiring and HR software covering recruiting, candidates, and employee records, used by talent teams managing the full hiring pipeline. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect Workable See the 37 actions ↓

HR and recruitingOAuth 2.0MCP + RESTworkable.com

AUDIT LOG · WORKABLEPOLICY: acme-support

09:41:07 · claude · u_8f2read

workable.list_employees

List Employees✓ allowed · 212ms

09:41:08 · claude · u_8f2read

workable.get_jobs

Get Jobs✓ allowed · 164ms

09:41:09 · claude · u_8f2write

workable.create_employee

Create Employee✓ approved · approved by user

09:41:12 · claude · u_8f2destructive

workable.delete_department

Delete Department✕ blocked · policy: deny

EVERY WORKABLE CALL, ON THE RECORD

01 · USE CASES

What agents do in Workable.

Get candidates for a job

Pull candidates in the pipeline for a specific job, a read-only status check.

Create an employee record

Add a new hire's employee record once they've accepted an offer.

Confirm before deleting a department

Check with the user before deleting a department, since jobs and employees may reference it.

02 · ACTIONS

37 Workable actions, graded by risk.

Every Workable action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

Look things up. Allowed by default.

workable.get_jobs
Get Jobs
workable.get_events
Get Events
workable.get_stages
Get Stages
workable.get_account
Get Account
workable.get_members
Get Members
workable.get_accounts
Get Accounts
workable.get_employee
Get Employee
workable.get_candidates
Get Candidates
workable.get_recruiters
Get recruiters
workable.list_employees
List Employees
workable.get_requisitions
Get Requisitions
workable.list_departments
List Departments
workable.list_public_jobs
List Public Jobs
workable.get_subscriptions
Get Subscriptions
workable.get_legal_entities
Get Legal Entities
workable.list_work_schedules
List Work Schedules

+ 9 MORE

write

Create and change things. Allow, or ask the user first.

workable.create_employee
Create Employee
workable.update_employee
Update Employee
workable.post_departments
Create Department
workable.post_member_enable
Enable Member
workable.post_members_invite
Invite Member
workable.post_background_check
Update Background Check Status
workable.put_members
Update Member
workable.put_departments
Update Department
workable.upload_employee_documents
Upload Employee Documents

destructive

Delete, cancel or archive. Ask first, or deny outright.

workable.delete_department
Delete Department
workable.delete_subscription
Delete Subscription
workable.post_department_merge
Merge Department

03 · HOW IT WORKS

Workable in three steps.

01Your users connect WorkableThey sign in to Workable on Arc0 Connect, under your brand, and approve the access you ask for.
02You set the rulesReads run, writes like “create Employee” can wait for the user, and “delete Department” can be denied outright.
03Any agent can actYour agent calls Workable through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.

POLICY.TS

await arc0.policies.set('workable', {
  read: 'allow',
  write: 'ask',        // create_employee
  destructive: 'deny',  // delete_department
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2

04 · AUTH AND DATA

How Workable connects.

Users sign in to Workable on Arc0 Connect and approve the scopes you request. Build with Arc0’s Workable OAuth app, or bring your own so the Workable consent screen names you. Tokens refresh automatically, and you can export them whenever you want.

The same Workable connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH: API key · OAuth 2.0
CREDENTIALS: Per-tenant encrypted vault
MODEL SEES: Results only, never credentials
AUDIT LOG: Every call, on every plan

05 · WORKS WITH

Use Workable from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

More hr and recruiting apps.

Greenhouse134 actions

Clockify75 actions

Lever64 actions

SAP SuccessFactors64 actions

ALL HR AND RECRUITING APPS →

07 · FAQ

Workable and Arc0, answered.

Q01

Can I use Workable with Claude, ChatGPT or Cursor?

Yes. Connect Workable to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Workable actions you allow.

Q02

How do users connect Workable?

Q03

Which Workable actions can my agent take?

37 in total: 25 read, 9 write and 3 destructive, such as “create Employee”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Workable?

Yes. Actions like “delete Department” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Workable too?

Yes. The same Workable connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Workable into your agent.

Your users connect Workable once, under your brand. Your agent gets 37 actions behind your policies, with every call on the record.

Connect Workable Browse all apps →

Free to build · MCP + REST · Audit log on every plan