Open Greenhouse MCP

Communauté Recherche et web

Greenhouse ATS for recruiting teams: role-based profiles (full, recruiter, read-only), pipeline views, analytics, candidate search and bulk operations.

Que pouvez-vous faire avec Open Greenhouse MCP ?

  • "Show me the pipeline for our Senior Engineer role"
  • "Who needs my attention this week?"
  • "What are our conversion rates for the Backend Intern role?"
  • "Find Sarah Chen and pull up her resume"
  • "Which sources are actually producing hires?"
  • "Bulk reject everything inactive for 30+ days on the Account Manager role"
  • "Screen this candidate for the Backend Engineer role — give me the full picture"
  • "Search our engineering pipelines for anyone with Rust and distributed systems experience"

Installation

Les étapes d'installation sont dans la documentation ci-dessous. Documentation

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. open-greenhouse-mcp
  2. Choose a Profile
  3. Quick Start
  4. What You Can Ask
  5. Safety
  6. Compatibility
  7. Startup
  8. What's Included
  9. Reference
  10. Feedback
  11. License

open-greenhouse-mcp

Production-ready MCP server for Greenhouse, designed for recruiters and hiring teams.

Most Greenhouse MCP servers mirror the API endpoint by endpoint. This one is built for recruiting teams: safe defaults, role-based profiles, and workflow tools that turn multi-step API operations into single actions.

Choose a Profile

ProfileToolsCan write?Recommended for
read-only104NoFirst-time setup, reporting, hiring managers
recruiter128Yes (safe ops)Day-to-day recruiting work
full187Yes (all)Admins, ops, advanced automation

Harvest v3. Greenhouse retired Harvest v1/v2 on 31 Aug 2026. From 0.5.0 this server uses Harvest v3 with OAuth 2.0 credentials. Upgrading from 0.4 or earlier? See Migrating from v1/v2.

Quick Start

pip install open-greenhouse-mcp

Add to your MCP client config (Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json, Cursor: Settings > MCP):

{
  "mcpServers": {
    "greenhouse": {
      "command": "open-greenhouse-mcp",
      "env": {
        "GREENHOUSE_CLIENT_ID": "your-harvest-v3-client-id",
        "GREENHOUSE_CLIENT_SECRET": "your-harvest-v3-client-secret",
        "GREENHOUSE_TOOL_PROFILE": "read-only"
      }
    }
  }
}

Start in read-only mode to validate connectivity and tool behaviour, then switch to recruiter or full when you need write access.

Create the credentials in Greenhouse under Configure > Dev Center > API Credentials > Create new API credentials > Harvest V3 (OAuth), and grant the scopes for the tools you plan to use. The client secret is shown once. See Advanced Setup for how tokens and scopes work.

What You Can Ask

  • "Show me the pipeline for our Senior Engineer role"
  • "Who needs my attention this week?"
  • "What are our conversion rates for the Backend Intern role?"
  • "Find Sarah Chen and pull up her resume"
  • "Which sources are actually producing hires?"
  • "Bulk reject everything inactive for 30+ days on the Account Manager role"
  • "Screen this candidate for the Backend Engineer role — give me the full picture"
  • "Search our engineering pipelines for anyone with Rust and distributed systems experience"
  • "What new applications came in since yesterday?"

See more examples with full output.

See it in action

Safety

  • Access is limited by the scopes on your Harvest v3 credential and the acting user's permissions
  • Read-only profile is recommended for first setup
  • Destructive actions require explicit IDs — the server never infers targets
  • Set GREENHOUSE_USER_ID and writes are made as that user (OAuth sub), so Greenhouse's audit trail shows who did what
  • Bulk actions are rate-limited to stay within API limits

Compatibility

ClientStatus
Claude DesktopSupported
Claude CodeSupported
CursorSupported
Transportstdio
Python3.10+

Startup

When the server starts, it logs its configuration:

open-greenhouse-mcp v0.5.0
Profile: recruiter | Tools: 128 | Writes: recruiter-safe | APIs: harvest-v3

What's Included

  • Screening & sourcing tools — 6 tools for candidate screening, resume search with boolean keywords, daily digest, and location detection
  • Recruiter workflow tools — 13 composite tools for pipeline views, analytics, search, and bulk operations
  • Harvest v3 API coverage — 154 tools across candidates, applications, jobs, offers, interviews, and more
  • Job Board API — 13 tools for public job listings and application submission
  • Optional webhooks and ingestion — 14 tools for event-driven workflows and partner integrations

Reference

Screening & Sourcing Tools

Tools for candidate evaluation and proactive talent search.

ToolWhat it does
screen_candidateComplete screening package — profile, resume text, location, screening answers, job description, history
fetch_new_applicationsApplications since a date, grouped by job — the daily recruiter digest
scan_pipeline_resumesSearch resume text across pipelines with boolean keywords (required/preferred/exclude)
search_pipeline_candidatesSearch pipelines by structured fields — title, company, education, experience, tags
scan_all_candidatesDatabase-wide candidate search by structured fields with date bounds
batch_read_resumesBatch-fetch and extract resume text for multiple candidates
Composite Tools

High-level tools that combine multiple API calls into single operations.

ToolWhat it does
pipeline_summaryFull pipeline view — candidates grouped by stage with names and days-in-stage
candidates_needing_actionFind stale applications and interviews missing scorecards
stale_applicationsApplications with no activity for N days, sorted by stalest
pipeline_metricsConversion rates, hire/rejection rates, time-in-stage per stage
source_effectivenessWhich candidate sources produce the best hire rates
time_to_hireAverage, median, min, max days from application to hire
bulk_rejectReject multiple applications in one call with rate-limit handling
bulk_tagTag multiple candidates in one call
bulk_advanceAdvance multiple applications to next stage
get_bulk_request_statusTrack a Greenhouse asynchronous bulk request (openings, custom field options)
search_candidates_by_nameFind candidates by first or last name
search_candidates_by_emailLook up a candidate by exact email
read_candidate_resumeDownload and return a candidate's most recent resume
download_attachmentDownload any Greenhouse attachment by URL
Profile Details

Recruiter includes all read tools, all screening/sourcing tools, all composite workflows, and recruiter-safe writes: reject, advance, hire, move, tag, notes, attachments, interviews, prospects, and bulk operations. It excludes job creation, user management, custom field configuration, candidate deletion, and webhook management.

Read-only skips all write operations. GREENHOUSE_READ_ONLY=true also works as a shorthand.

Configuration
VariableRequiredDescription
GREENHOUSE_CLIENT_IDYes*Harvest v3 OAuth client ID
GREENHOUSE_CLIENT_SECRETYes*Harvest v3 OAuth client secret
GREENHOUSE_BOARD_TOKENYes*Job board URL slug. *Harvest credentials and/or a board token required
GREENHOUSE_USER_IDNoGreenhouse user ID: writes are made as this user, and the tool profile is derived from their role
GREENHOUSE_TOOL_PROFILENofull (default), recruiter, or read-only (ignored when GREENHOUSE_USER_ID is set)
GREENHOUSE_BOARD_API_KEYNoJob Board API key, for submitting applications through the board
GREENHOUSE_INGESTION_API_KEYNoIngestion API key, for partner candidate submission
GREENHOUSE_LOG_LEVELNodebug, info, warning (default), error
GREENHOUSE_LOG_FILENoLog file path (defaults to stderr)
Logging

Structured JSON logging for observability. Set GREENHOUSE_LOG_LEVEL=info to enable:

{"ts": "2026-04-14T12:31:58", "level": "info", "event": "api_call", "method": "GET", "url": "...", "status": 200, "latency_ms": 245.0}
More Documentation
  • API Reference — Full tool breakdown by category
  • Usage Examples — Real conversations with full output
  • Advanced Setup — Harvest v3 credentials and scopes, migrating from v1/v2, webhook receiver, ingestion API, board-token mode
  • Development — Contributing, testing, project structure

Feedback

License

MIT License -- Ben Monopoli. See LICENSE.

Questions fréquentes

Qu'est-ce que Open Greenhouse MCP ?

Greenhouse ATS for recruiting teams: role-based profiles (full, recruiter, read-only), pipeline views, analytics, candidate search and bulk operations.

Comment installer Open Greenhouse MCP ?

Suivez les étapes d'installation de sa documentation, affichée sur cette page et dans son dépôt.

Open Greenhouse MCP est-il open source ?

Oui. Son code est sur GitHub sous licence MIT.

Qui maintient Open Greenhouse MCP ?

Il est publié par benmonopoli. AI.tn le référence sans le maintenir ni le recommander.

Issu des listes communautaires awesome-mcp-servers et du dépôt GitHub du projet. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.