Greenhouse MCP server for AI agents

Live

OAUTH 2.0

RECRUITING

Productivity

Greenhouse gives your agent recruiting operations in your ATS: track candidates and applications through interview stages, record interviews and scorecards, manage jobs and openings, and create offers.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Greenhouse
agent · Acme Q3
Run
Which applications for the Senior Backend Engineer job are waiting on scorecards?
S
greenhouse_scorecards_list
132ms
Recruiting agent
5 applications had interviews last week without a submitted scorecard. 3 of them are waiting on the same interviewer.
Sources: Greenhouse scorecards, 1 job
greenhouse
5 applications
18:29
Message Claude...

Tools your recruiting agent reaches for on Greenhouse, scoped per user.

CALL ANY TOOL
90 tools for recruiting in Greenhouse: candidates, applications, interviews, scorecards, jobs, job posts, openings, offers, notes, and tags, with stage moves, rejections, and hires.
greenhouse_application_convert_to_candidate
Application convert to candidate
Convert a Greenhouse prospect application into a candidate application on a specific job, optionally at a chosen interview stage. Returns the new candidate application; the prospect application's status becomes converted. Use this when a prospect is ready to interview. Use greenhouse_application_create to add a fresh application instead. Requires a prospect application id from greenhouse_applications_list (prospect true) and a job_id the prospect is attached to.
Parameters
Name
Type
Required
Description
application_id
integer
Required
Id of the application to act on. Get it from greenhouse_applications_list. Example: 4012345002
job_id
integer
Required
Id of the Greenhouse job. Get it from greenhouse_jobs_list. Example: 4012345002
to_job_interview_stage_id
integer
Optional
Id of the job interview stage to place the new candidate application in. Defaults to the job's first stage. Get it from greenhouse_job_interview_stages_list. Example: 4012345002
greenhouse_application_create
Create application
greenhouse_application_delete
Delete application
greenhouse_application_move
Move application
greenhouse_application_stages_list
List application stages
greenhouse_application_update
Update application
greenhouse_attachment_create
Create attachment
greenhouse_attachments_list
List attachments
greenhouse_candidate_delete
Delete candidate
greenhouse_candidate_employment_create
Create candidate employment
greenhouse_candidate_tag_delete
Delete candidate tag
greenhouse_candidate_tags_list
List candidate tags
greenhouse_custom_fields_list
List custom fields
greenhouse_email_templates_list
List email templates
greenhouse_job_boards_list
List job boards
greenhouse_job_create
Create job
greenhouse_job_interview_stages_list
List job interview stages
greenhouse_job_note_delete
Delete job note
greenhouse_job_note_update
Update job note
greenhouse_job_owner_create
Create job owner
greenhouse_job_post_locations_list
List job post locations
greenhouse_job_post_update
Update job post
greenhouse_notes_list
List notes
greenhouse_offer_create
Create offer
greenhouse_opening_update
Update opening
greenhouse_prospect_details_list
List prospect details
greenhouse_referrers_list
List referrers
greenhouse_rejection_reason_get
Get rejection reason
greenhouse_scorecard_question_options_list
List scorecard question options
greenhouse_sources_list
List sources

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Greenhouse tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["greenhouse"], toolNames: [
    "greenhouse_applications_list",
    "greenhouse_scorecards_list",
    "greenhouse_application_move"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Move Onsite applications for the Product Designer job with submitted scorecards to the Offer stage" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["greenhouse"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Move Onsite applications for the Product Designer job with submitted scorecards to the Offer stage" }],
  tools,
});

// Execute the tool call with the user's vaulted Greenhouse OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["greenhouse"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Move Onsite applications for the Product Designer job with submitted scorecards to the Offer stage" }],
  tools,
});

// Tool call runs with the user's vaulted Greenhouse OAuth token
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["greenhouse"] }, pageSize: 100,
});

const agent = new Agent({
  name: "recruiting_agent",
  model: "gemini-2.5-pro",
  instruction: "Greenhouse tools scoped to this user",
  tools,
});

await agent.run("Move Onsite applications for the Product Designer job with submitted scorecards to the Offer stage");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Greenhouse tool. Click to copy, paste into your agent, done.
Pipeline
Copy the prompt
Copied
List active applications for the Product Designer job in the Onsite stage.
Copy the prompt
Copied
Move Priya Shah's application to the Offer stage.
Copy the prompt
Copied
Reject the application from jordan@example.com with the reason Not a fit and no email.
Interviews
Copy the prompt
Copied
Show this week's scheduled interviews for the Senior Backend Engineer job.
Copy the prompt
Copied
Which interviewers have not submitted scorecards for last week's interviews?
Copy the prompt
Copied
Add a note to Maria Lopez's profile summarizing today's phone screen.
Jobs and offers
Copy the prompt
Copied
Create a Data Analyst job from the Analyst template with 2 openings.
Copy the prompt
Copied
List offers sent this month and their status.
Copy the prompt
Copied
Publish the Customer Success Manager job post.
SEE HOW AUTH WORKS
Each user signs in to Greenhouse once, and Scalekit stores and refreshes their tokens. Tokens stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
Greenhouse
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Greenhouse
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Greenhouse
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Greenhouse
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other recruiting and HR connectors.
People Ops and HR teams
Offer letter routing agent
Drafts the offer in PandaDoc, blocks on the hiring manager's approval in Slack, then emails the candidate their e-signature link. Every call runs as the recruiter who triggered it, never a shared HR bot.
Support and Ops Teams
Meeting prep
Pulls agenda, participant context, and open action items before every meeting.
Test other agents
See the same per-user auth pattern across other recruiting and HR connectors.
PEOPLE OPS
Offer letter routing agent
Draft the offer in PandaDoc, gate it on hiring manager approval in Slack, then email the candidate their signature link.
OPS
Meeting prep agent
Assemble the agenda, HubSpot attendee history, and open action items from Gmail before every meeting on the calendar.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Greenhouse token looks fine in a demo. In production every stage move and rejection looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Greenhouse today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Greenhouse as the user or through a shared service account?
As the user. Each user signs in to Greenhouse once, and Scalekit stores and refreshes their tokens. Stage moves, notes, and scorecards the agent records are attributed to that user in your audit trail, not a shared service account.
Where is the Greenhouse OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in Greenhouse?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example the list tools and greenhouse_note_create without greenhouse_candidate_delete, which permanently deletes a candidate with all of their applications, attachments, scorecards, and notes. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Greenhouse access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Does the agent create calendar events for Greenhouse interviews?
No. greenhouse_interview_create records an interview on a Greenhouse application for an event that already exists on your own calendar, with its panel, time, location, and video link. Greenhouse does not create the event or send invites, so pair it with a calendar connector.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""greenhouse"": {
""url"": ""https://mcp.scalekit.com/greenhouse"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.greenhouse]
url = ""https://mcp.scalekit.com/greenhouse""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""greenhouse"": {
""url"": ""https://mcp.scalekit.com/greenhouse"",
""type"": ""http""
}
}
}