EasyHire AI MCP server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@EasyHire AI MCP serverFind my open jobs and import these candidate profiles."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
EasyHire AI for Codex
Open-source Codex integration for creating or selecting EasyHire AI jobs and importing complete candidate profiles through a hosted Remote MCP server.
What Is Open Source
This repository contains:
Remote MCP server adapter
MCP tool contracts
EasyHire API client
Codex installer
Candidate import Skill
Tests, Docker packaging, and deployment documentation
EasyHire AI databases, customer data, membership logic, scoring prompts, internal services, and production secrets are not included.
Related MCP server: Recruit CRM MCP
Install
After the package and production MCP endpoint are published:
npx -y @easyhireai/codex@latest setupThe installer adds the hosted MCP server, opens EasyHire OAuth login, installs the global Skill, and verifies the connection. It does not store OAuth tokens.
Tools
find_jobs
Find an open job owned by the authenticated EasyHire AI user, or list recent open jobs.
import_candidates_to_job
Accept up to 50 complete LinkedIn profile payloads and one required job_id.
The backend creates or reuses candidates, binds them to the job, and starts the
existing resume cleaning and JD Match scoring workflow.
Contact-only records and generated summaries are intentionally rejected.
create_or_continue_job
Create a job from a validated JobBriefV1, or answer pending Intake questions
on the same EasyHire Agent job session. Repeated identical briefs reuse the
same creation result for 24 hours.
Local Development
Requirements: Node.js 20+, pnpm 11+, and a running EasyHire Python API.
pnpm install
cp apps/mcp-server/.env.example apps/mcp-server/.env
pnpm check
pnpm dev:mcpThe local MCP endpoint is http://127.0.0.1:8787/mcp.
EASYHIRE_MCP_AUTH_MODE=backend is only for local integration against an
EasyHire API that validates the forwarded bearer token. Production must use
EASYHIRE_MCP_AUTH_MODE=jwt.
Security
The MCP server never connects directly to the EasyHire database. It forwards a verified bearer token to documented EasyHire API endpoints. Logs exclude access tokens and candidate profile contents.
Candidate import is available to every active EasyHire AI membership tier. Non-members are rejected by the backend, and existing AI-credit rules apply when imported candidates enter JD Match.
See SECURITY.md and docs/oauth.md.
The required EasyHire API surface is documented in docs/backend-api-contract.md.
License
Apache-2.0.
This server cannot be deployed
Maintenance
Related MCP Connectors
isolved and ApplicantPro jobs, tenant discovery, and change detection as an MCP server.
- Cavuno MCPOAuthcom.cavuno
Connect Claude, Cursor, Codex, and other MCP clients to manage your Cavuno job board.
- ZapierOAuthcom.zapier
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
GetJobzi MCP server for job search, application tracking, and career forecasting.
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables resume parsing, querying, and email notifications via MCP tools.31-
- AlicenseAqualityCmaintenanceMCP server for Recruit CRM, enabling AI assistants to search candidates, view jobs, and manage recruiting workflows.53MIT
- FlicenseNot gradedqualityDmaintenanceMCP server that connects AI agents to Homerun, an applicant tracking system. Enables AI-assisted candidate review: browse vacancies, inspect applications, and leave review notes.-
- AlicenseNot gradedqualityCmaintenanceAn MCP server that exposes job-search and application-management capabilities to compatible AI clients, enabling discovery of vacancies, drafting of tailored application materials, and coordinated human-approved submissions.MIT