ChatGPT + Greenhouse: What the Integration Can (and Can't) Do in 2026
Yes, ChatGPT can connect to Greenhouse — through Greenhouse MCP, the official Model Context Protocol server Greenhouse announced May 7, 2026 and began rolling out to customers in June. It’s not an app in ChatGPT’s directory; it’s a governed endpoint your org connects to approved AI tools — Greenhouse names ChatGPT, Claude, Copilot Studio, Gemini CLI, Grok, and Amazon Q. Every call goes through a curated set of MCP tools tied to your existing Greenhouse permissions and audit trails, with rate and safety limits built in. Once connected, you can interrogate your pipeline in plain English — and like every connector in ChatGPT, it works in a session you’re driving. Between chats, nothing watches your candidates move through stages.
Here’s what the ChatGPT Greenhouse integration actually does, how to turn it on, and what to use when you want recruiting work that runs without you.
What ChatGPT can actually do with Greenhouse
- Analyze your pipeline conversationally. “How’s the Staff Backend Engineer pipeline trending vs. last quarter?” — answered from live Greenhouse data, respecting what your role can see.
- Run investigations across multiple jobs. Greenhouse’s own launch examples include complex investigations spanning several requisitions and QBR-style summaries that used to mean an afternoon of report-building.
- Blend hiring data with other systems. Cross-system views that combine Greenhouse data with HRIS or finance data connected in the same session — cost-per-hire by department, offer-accept rates against comp bands.
- Generate compliance-ready audit narratives. On-demand write-ups of who did what in a hiring process, tied to Greenhouse’s audit trail.
- Update candidate statuses via defined tools. The MCP exposes governed write actions like candidate status updates — what’s available depends on the tools your org enables.
- Run inside agent sessions. With ChatGPT Work (launched July 9, 2026), you can @-mention connected apps and let an agent work across Greenhouse and the rest of your stack in a long, metered run — a full-funnel hiring retro, say. Still a run you start.
How to set it up
- Be on a Greenhouse plan with MCP access — it began rolling out to customers in beta in June 2026 — and have an admin who can approve AI-tool connections. This is an org-level decision, not an individual toggle.
- In Greenhouse, an admin enables MCP and configures which tools and AI clients are approved, following Greenhouse’s self-service documentation.
- In ChatGPT, open Settings → Connectors → Add custom connector (Pro, Business, and Enterprise plans) and point it at your Greenhouse MCP endpoint, authenticating as yourself.
- Ask a pipeline question (“which open roles have had no candidate movement in two weeks?”) — access mirrors your Greenhouse permissions.
The limits that actually matter
- It doesn’t run on triggers. There’s no “when a candidate reaches offer stage, draft the offer email” or “when an interview is scheduled, brief the panel.” ChatGPT queries Greenhouse when you prompt it — it never fires on a Greenhouse event.
- Curated tools, not the whole ATS. The initial release is deliberately a curated set of MCP tools with expanded coverage promised over time. If a workflow needs an action Greenhouse hasn’t exposed yet, the connector can’t do it.
- Governance is the point — and the gate. Permission-aware access and org-level controls mean candidate data stays as gated in ChatGPT as it is in Greenhouse. Recruiters see their pipelines; nobody’s API key quietly widens access. Good for compliance, but it also means IT is in the loop before anyone connects.
- Session-bound, even in agent mode. ChatGPT Work runs are long and autonomous but manually started and metered against your plan’s allowance — an errand, not a standing watch on your pipeline.
If you want Greenhouse work that runs on its own: Carly
The moment you want something to happen off a hiring event — a candidate moves to offer stage and the offer email drafts itself while a call goes on the calendar, hiring managers get a pipeline digest every Monday morning, a role that sits stale for ten days gets flagged to the recruiter — you’ve crossed past what a governed query endpoint is for.
That’s where Carly fits. Carly is an AI executive assistant that acts on triggers across your whole stack, set up by conversation instead of code:
- Fires on events and schedules, 24/7, in the cloud. Stage change, new application, Monday 8am — Carly acts without a chat open.
- No-code setup. Tell Carly “when a candidate moves to offer stage in Greenhouse, draft the offer email and schedule the call” in plain English; it interviews you and builds the workflow.
- Connects recruiting to the rest of your work — Greenhouse data flowing into email, calendars, Slack, and spreadsheets in one flow.
- Actually sends — drafts and sends email across Gmail and Outlook, schedules interviews, manages tasks.
- Connects to anything — 200+ native integrations, plus any other tool via your own API key. Carly connects to Greenhouse with your own Harvest API key — paste it on carlyassistant.com/integrations and Carly can read and act on your pipeline in workflows.
AI agents start at $35/month, and steps in a workflow that don’t use AI run free and unlimited. See integrations for the full list.
ChatGPT vs Carly
| ChatGPT (Greenhouse MCP) | Carly | |
|---|---|---|
| Pipeline analysis & investigations | Yes | Yes |
| Cross-system hiring views | Yes, in-session | Yes, in workflows |
| Monday pipeline digest, unprompted | No | Yes, on a schedule |
| Reacts to a stage change by itself | No | Yes, on any trigger |
| Runs without a session open | No (agent runs are started + metered) | Yes (cloud, 24/7) |
| Drafts and schedules the offer call | No | Yes |
| Emails hiring managers for you | No | Yes (Gmail + Outlook) |
| Setup | Admin enables MCP, add connector | Paste your Harvest API key, describe the workflow |
| Pricing | Paid ChatGPT plan + Greenhouse MCP | AI agents from $35/mo |
ChatGPT over Greenhouse MCP is a recruiting analyst you question in a chat. Carly is an assistant that acts on your pipeline while you’re doing something else.
Frequently Asked Questions
Does ChatGPT work with Greenhouse?
Yes, via Greenhouse MCP — the official MCP server Greenhouse announced May 7, 2026 and began rolling out in June. Your org enables it, then you add it to ChatGPT as a custom connector. It’s governed: every call goes through defined tools tied to existing permissions and audit trails.
Is Greenhouse MCP an app in ChatGPT’s directory?
No. Unlike vendors that shipped directory apps, Greenhouse ships a governed MCP endpoint that orgs connect to approved AI tools — ChatGPT, Claude, Copilot Studio, and others. An admin has to enable it before anyone connects.
Can ChatGPT react to a Greenhouse event automatically?
No. ChatGPT queries Greenhouse inside a session you start — it doesn’t watch for stage changes, new applications, or stalled roles. For “when a candidate hits offer stage, draft the email and book the call,” you need a trigger-based assistant like Carly, which connects to Greenhouse with your own Harvest API key.
How do I connect ChatGPT to Greenhouse?
Ask your Greenhouse admin to enable Greenhouse MCP and approve ChatGPT as a client, then add the endpoint in ChatGPT under Settings → Connectors → Add custom connector and authenticate. Your access mirrors your Greenhouse permissions.
More: ChatGPT email assistant · ChatGPT personal assistant · ChatGPT MCP · Can ChatGPT send emails · Claude + Greenhouse · Best AI workflow automation tools
Ready to automate your busywork?
Carly schedules, researches, and briefs you—so you can focus on what matters.
See what people say
"Before Carly, I relied on a Calendly link, but the whole process felt impersonal and not very professional. Carly changed that by handling all the back-and-forth, so I'm no longer stuck in endless email threads trying to line up schedules.
Now Carly reaches out to candidates, shares my real-time availability, lets them pick a slot, then sends a Zoom link and drops it straight into my calendar. She sends reminders to both of us before each call, which has significantly reduced no-shows and last-minute confusion.
On top of scheduling, Carly acts like a full executive assistant, sending me my schedule the night before so I can prepare for each call. It reminds me of the old x.ai assistant, but Carly is noticeably smarter, faster, and better suited to my healthcare recruitment business."
