NEW YORK — Greenhouse, the leading hiring platform, today announced the Greenhouse MCP (Model Context Protocol), a new capability that gives customers a governed way to connect AI tools directly to Greenhouse. Developed with input from customer design partners, including StubHub and Komodo Health, the Greenhouse MCP will be rolled out to customers starting in June.
AI agents, software tools that can act autonomously on a user’s behalf, are already reshaping how candidates look for work. According to Greenhouse’s latest survey of over 2,950 active job seekers, 30% are already using AI agents to search for openings, submit applications, and schedule interviews. As candidates’ behavior shifts, hiring teams face growing pressure to deploy an array of AI tools – without stepping outside the systems and controls that govern how hiring decisions are made.
But connecting powerful models to sensitive hiring data has been difficult to do safely. Many organizations want to automate and improve existing workflows, enable new kinds of actions across systems, and experiment with AI-assisted ways of working. Doing that outside the hiring system of record creates risk. The Greenhouse MCP is designed for exactly those goals, a standard, permission-aware way for approved AI tools and agents to connect to Greenhouse, inside the structure teams already rely on.
“AI should strengthen hiring, not shortcut it,” said Meredith Johnson, Chief Product Officer of Greenhouse. “The Greenhouse MCP gives teams the flexibility to connect the AI tools they’re already using, and the controls to make sure that access stays structured, accountable, and inside the system of record. Recruiting teams can unlock new workflows without breaking the process.”
With the Greenhouse MCP, customers can:
- Automate existing workflows, such as QBR and board-ready hiring summaries, pipeline bottleneck analysis, candidate status roundups, and offer and forecast digests.
- Use conversational prompts to take high-value actions that were nearly impossible before, including complex investigations spanning multiple jobs, cross-system views that blend Greenhouse data with HRIS or finance data, and compliance-ready audit narratives generated on demand.
- Experiment with future AI-native experiences, such as internal hiring copilots in Slack or Microsoft Teams, TA Ops agents that help keep pipelines clean, and assistants that answer nuanced hiring questions in plain language.
“The MCP server democratizes the access to recruiting intelligence,” said Matt Texeira, Senior Director, Global Talent Acquisition at Komodo Health. “The [Greenhouse MCP] beta has been great for powering meaningful pipeline analytics for hiring managers via dashboard-style visuals. Something that used to take entire Business Intelligence teams to stand up now gets delivered in under 30 minutes. This helps recruiters approach conversations with data-backed guidance.”
The Greenhouse MCP extends the same principles that define how Greenhouse builds and deploys AI across its platform: structure first, governed access, and explainability and control at every step. Every MCP call goes through defined tools, tied to existing permissions and audit trails, so teams can see and govern what is happening. For customers, that means AI projects can move forward inside a framework that is understandable to security, legal, and compliance teams.
The initial release focuses on the foundations customers need to start safely: a curated set of MCP tools, organization-level controls, permission-aware access, rate and safety limits, and documentation for self-service integration. Greenhouse will continue to use customer feedback during this initial MCP release phase to inform enhancements such as hardened guardrails, expanded coverage, and more connections over time.
