"Screen these 3 resumes against the Senior React job and tell me who to interview."

Your assistant parses each CV, extracts the job criteria, scores every candidate criterion by criterion and explains the shortlist.

Contents

• What you can do
• Quick start
• Install in your MCP client
• Tools
• Example prompts
• Pricing and credits
• Data and privacy
• Troubleshooting
• FAQ

What you can do

• Parse resumes and CVs. Turn PDF, Word, image and other files into structured JSON: contact details, work experience, education, languages, skills and the full text. Scanned resumes go through OCR, and the resume language is detected.
• Turn a job description into criteria. Get weighted, explained matching criteria, with mandatory requirements flagged.
• Match candidates to jobs. Score a resume against a job from 0 to 1, with an explanation for each criterion.
• Rank candidates. Order up to 10 candidates for the same job in one call, with a score and a rationale for each.
• Normalize skills. Map free-text skills in French or English to a skills taxonomy with stable IDs.

Use it to screen applicants in a chat, build a recruiting agent, enrich an ATS, or prototype HR tech features without writing integration code.

Quick start

1. Add the server URL https://hirelayer.co/mcp in your AI app, or click a one-click install button above.
2. Sign in to HireLayer when your app asks, and allow access. No account yet? Sign up for free: 50 credits a month, no card required.
3. Ask your assistant. For example: attach a resume and ask "Summarize this candidate."

To try it without your own data, use the sample job and resumes in examples/. The repository ships a .mcp.json: clone it, export HIRELAYER_API_KEY, open the folder in Claude Code and it offers to enable the local server.

Install in your MCP client

Hosted server (recommended)

Connect to https://hirelayer.co/mcp and sign in to HireLayer. Nothing to install, nothing to keep up to date.

Clients that cannot sign in with OAuth can send a HireLayer API key instead: Authorization: Bearer your-api-key.

The hosted parse_resume takes a file attached in ChatGPT, a public HTTPS URL, a small file in base64 or the resume text. To parse files from your disk, run the server locally.

Local server (npx)

Runs on your machine with an API key: sign up, then copy your key from Dashboard → API keys and replace your-api-key below.

claude mcp add hirelayer --env HIRELAYER_API_KEY=your-api-key -- npx -y hirelayer-mcp

{
  "mcpServers": {
    "hirelayer": {
      "command": "npx",
      "args": ["-y", "hirelayer-mcp"],
      "env": { "HIRELAYER_API_KEY": "your-api-key" }
    }
  }
}

{
  "mcpServers": {
    "hirelayer": {
      "command": "npx",
      "args": ["-y", "hirelayer-mcp"],
      "env": { "HIRELAYER_API_KEY": "your-api-key" }
    }
  }
}

{
  "inputs": [
    { "type": "promptString", "id": "hirelayer_api_key", "description": "HireLayer API key", "password": true }
  ],
  "servers": {
    "hirelayer": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "hirelayer-mcp"],
      "env": { "HIRELAYER_API_KEY": "${input:hirelayer_api_key}" }
    }
  }
}

{
  "mcpServers": {
    "hirelayer": {
      "command": "npx",
      "args": ["-y", "hirelayer-mcp"],
      "env": { "HIRELAYER_API_KEY": "your-api-key" }
    }
  }
}

codex mcp add hirelayer --env HIRELAYER_API_KEY=your-api-key -- npx -y hirelayer-mcp

gemini mcp add -e HIRELAYER_API_KEY=your-api-key hirelayer npx -y hirelayer-mcp

docker build -t hirelayer-mcp .
docker run -i --rm -e HIRELAYER_API_KEY=your-api-key hirelayer-mcp

Tools

All tools only read and analyse data. They never change anything in your systems.

The server also ships prompts that clients show as ready-made commands:

How screening works

flowchart LR
    J[Job description] --> C[extract_job_criteria]
    R[Resume files] --> P[parse_resume]
    C --> M[match_candidate]
    P --> M
    P --> K[rank_candidates]
    J --> K
    M --> S[Shortlist with explanations]
    K --> S