Workable MCP connector
Connect Workable to Elaichi and Claude, ChatGPT, Cursor or any MCP client can search jobs, review candidates, add new ones, move them through stages and update records, all within the signed-in person's own Workable access.
-
How it connects. Connects over OAuth. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect Workable to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Workable once
-
Open Connections, choose Add connection, and pick Workable.
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in Workable. Workable's own window opens. Whoever approves it decides what this connection can reach.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Workable MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Workable MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Workable MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Workable to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Workable through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Recruiting
Catch a candidate up after a screen
Finish a phone screen, say what you learned, and the candidate's record in Workable is updated and moved to the next stage while it is still fresh.
-
Recruiting
Give a strong runner-up another job
When a good candidate loses out on one role, copy or relocate them to a better matching open job in Workable instead of letting them go cold.
-
Hiring managers
See where a job's pipeline stands
Ask how many candidates sit at each stage of your open role, who has been waiting longest, and what happened on it this week, without opening Workable.
-
Sourcing
Add found profiles to the talent pool
Paste the details of someone promising and they land in the Workable talent pool or on a specific job, ready for the recruiter to pick up.
-
Recruiting coordinators
Clear the queue of pending decisions
Advance the candidates the panel approved, disqualify the rest with a reason, and reverse a disqualification when a manager changes their mind.
-
People Ops
Check an offer before the start date
Pull up a candidate's offer, their files and the activity on their application so onboarding begins with the right title, salary and start date.
Try asking
- “Which candidates moved to the offer stage this week?”
- “Show open jobs with nobody past the phone screen stage.”
- “Move Priya Shah to the interview stage for Account Executive.”
Compare
Elaichi vs Zapier MCP vs Composio for Workable
All three can connect Workable to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Workable tools | Allow or restrict single Workable tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Workable call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
AI tools
Workable tools for your AI agents
94 tools are ready to call through Elaichi's MCP endpoint the moment you connect Workable, governed by the same roles, restrictions, and audit log as everything else in Elaichi. Workable builds and runs these tools.
No tools match your search.
See it in Elaichi
What connecting Workable gets you
6 screens from the product, each doing one job for your Workable account.
The agent
Ask about candidates, get answers from Workable.
Type a question about a job or candidate and the agent reads live Workable records.
- jobs
- candidates
- stages
- offers
Ask Elaichi to work across your apps.
Which candidates moved to the offer stage this week?
Show open jobs with nobody past the phone screen stage.
Move Priya Shah to the interview stage for Account Executive.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Workable in Claude, ChatGPT and Cursor at once.
One governed endpoint, every MCP client, no SDK and no shared API key.
Copy the endpoint
Tool catalog
94 Workable tools, no code to write.
Jobs, candidates, stages, offers and files, covered without building a line of custom code.
- Get accounts
- Get jobs
- Search jobs
- Get job
Toolboxes
Each team gets its own Workable toolbox.
Recruiters, hiring managers and sourcers each see the Workable tools their work needs.
- Recruiting
- Hiring managers
- Sourcing
- Coordinators
Shared connections
One Workable connection, shared without sharing passwords.
See who connected each Workable account and which teams and members work through it.
- Recruiting
- Engineering hiring
- Sales hiring
- Sourcing
Audit log
Every Workable action has a name on it.
When, who, what happened and which candidate or job, in an append-only log.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
The pipeline digest writes itself each morning.
New Workable candidates are fetched, grouped by job, drafted, approved by a person, then posted back.
Workable digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch jobs
Workable
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Workable
Queued
Collections and dashboards
Hiring numbers from Workable, computed without a model.
Four metrics, 14 days of candidates created and a split by team, refreshed on schedule.
Workable health
Refreshed 4 minutes ago · every 15 minutes · from the jobs collection
Jobs
1,284 ↓ 12%
Candidates
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Jobs created
Last 14 days
By team
Share of activity
Recruiting 34%
Engineering hiring 27%
Sales hiring 21%
Sourcing 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Workable to Claude?
Connect Workable in Elaichi first: Workable opens its own sign-in window, you log in as yourself and approve, and that is the whole step. There is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude signs you in through Elaichi and your Workable jobs and candidates are available.
Does Workable work with ChatGPT and Cursor as well as Claude?
Yes. Once Workable is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Workable once and every client you use picks it up.
What can an AI agent actually do with my Workable data?
With Workable connected, an agent can find open jobs, read a job's stages, recruiters and application form, list the candidates in a pipeline and read their activity, files and offer. It can also add a candidate to a job or the talent pool, update a candidate, move them to another stage or job, and disqualify them or reverse that. Short, concrete asks such as "move Dana to the interview stage on the Account Executive job" work better than long instructions.
Does connecting Workable give the AI access to every job and candidate?
No. Every request runs as the person who signed in, so an agent only sees the Workable jobs and candidates that person can already see, with Workable's own member and recruiter rules still applying. Elaichi can narrow that further, by team or by action, but it can never widen it beyond what Workable already allows.
Can I stop an agent from deleting or changing things in Workable?
Yes. Restrictions in Elaichi apply per action, so you can allow reading Workable jobs and candidates while blocking moves, disqualifications or updates. A restricted action is never advertised to Claude, ChatGPT or any other client, so no prompt, however worded, can reach it.
What happens to a Workable connection when someone leaves?
Offboarding a person in Elaichi ends their access to Workable through every client at once. If they shared a Workable connection with the team, it keeps working for everyone else. Disconnecting Workable once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client at the same time.
Does the Workable MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Workable is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for Workable?
Yes. Both let Claude, ChatGPT or Cursor use Workable. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Workable call.
How is Elaichi different from Composio for Workable?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Workable: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Workable in front of your team
14 days on Gold, no credit card. Connect it once and pick what each team can call.
- Works with
-
and any other MCP client, or the Elaichi Agent.
- When the trial ends
- Nothing is deleted. Connections, roles and the audit log stay where they are, so subscribing picks up exactly where you left off.