Skip to content

ChatGPT integration · MCP server

Parse resumes and screen candidates in ChatGPT

HireLayer’s MCP server gives ChatGPT real recruiting tools instead of guesswork: structured resume parsing, weighted job criteria, explained candidate scores and rankings. Add one URL, sign in to HireLayer, and ask in plain language.

Server URL
https://hirelayer.co/mcp
Sign-in
OAuth with your HireLayer account, no key to paste
Plans
Business, Enterprise, Edu; Pro in developer mode
Cost
1 credit per resume parsed or scored; criteria are free
ChatGPT + HireLayer
  1. 1You askChatGPT“Here are 4 CVs and our Senior Data Engineer job. Who should we interview?”
  2. 2extract_job_criteriaHireLayerThe job description becomes weighted criteria, with must-haves flagged.
  3. 3parse_resume + score_resumesHireLayerEach attached CV is parsed, then scored from 0 to 1 with an explanation per criterion.
  4. 4ChatGPT answersChatGPTA shortlist table with scores, mandatory criteria met and gaps, and who to interview first.

What recruiters ask ChatGPT with HireLayer connected

  • Summarize an attached CV

    “Summarize this candidate: current role, years of experience, key skills, languages, availability.” ChatGPT parses the file with HireLayer instead of skiming the PDF.

  • Screen a batch against a job

    “Score these resumes against this job and give me a table.” Every candidate is checked against the same weighted criteria, with an explenation you can audit.

  • Rank a shortlist

    “Rank these 8 candidates for the Account Executive role and explain the top 3.” One call scores up to 50 candidates and re-ranks the 10 best.

  • Normalize skills

    “Map this skills section to standard skills.” Free text such as “MS Office, fluent English” becomes taxonomy skills with IDs.

Add HireLayer to ChatGPT

ChatGPT connects to remote MCP servers from the web app. On Business, Enterprise and Edu workspaces an admin may need to allow custom MCP servers first.

  1. 1

    Add a custom MCP server

    In ChatGPT on the web, open Plugins, select + and Add custom MCP server. Name it HireLayer and paste the server URL. On Pro, turn on developer mode first.

    Server URLtext
    https://hirelayer.co/mcp
  2. 2

    Choose OAuth and sign in

    Pick OAuth authentication. ChatGPT opens the HireLayer sign-in page: log in or create a free account (50 credits a month, no card) and allow access.

  3. 3

    Check the tools

    ChatGPT lists the six tools it found: parse_resume, extract_job_criteria, score_resumes, search_resumes, search_jobs and normalize_skills. All but normalize_skills save what they process (resumes, jobs, scores) to your HireLayer account, like the API, so ChatGPT can ask you to confirm them; normalize_skills is read-only.

  4. 4

    Use it in a chat

    Select HireLayer with @ in the composer, attach a CV or paste a job description, and ask. ChatGPT picks the tools and explains the results.

A screening prompt that works well

Give ChatGPT the job, the CVs and the output you want. HireLayer’s results follow the job’s language (English, French, German, Spanish or Portuguese; English for any other); ChatGPT translates them when it answers in another language.

Prompttext
@HireLayer Screen the 4 attached CVs for this job.
1. Extract the criteria from the job description.
2. Parse each CV and score it against the same criteria.
3. Give me a table sorted by score: candidate, score,
   mandatory criteria met, main gaps.
4. Recommend who to interview and why.

Job description:
Senior Data Engineer, Paris (hybrid). 5+ years of Python and SQL,
Airflow or Dagster, a cloud data warehouse (BigQuery or Snowflake)…

Good to know

  • Plans and admins

    OpenAI documents full MCP support for Business, Enterprise and Edu, with read/fetch tools for Pro in developer mode. Only normalize_skills is read-only among HireLayer’s six tools; the others also save resumes, jobs or scores to your account. Workspace admins control who can add custom MCP servers.

  • Web app first

    Custom MCP servers are added and used from ChatGPT on the web. Availability in the desktop and mobile apps follows OpenAI’s rollout.

  • Parsing takes about 35 seconds

    ChatGPT waits for each parse. For ten CVs, ask it to score the resume texts in one score_resumes call rather than parse each file first, to save time and credts.

  • Human decision

    Scores and rankings support a recruiter’s decision. They never replace it.

HireLayer and ChatGPT: questions

Can ChatGPT parse resumes?

ChatGPT can read a CV, but it does not return a consistent structure. With HireLayer connected, it calls a resume parser that returns the same fields every time: contact details, work history, education, languages and skills.

Is HireLayer in the ChatGPT plugin directory?

Not yet. Add it as a custom MCP server with the URL https://hirelayer.co/mcp; it works the same way.

Do I need an API key?

No. ChatGPT signs in to HireLayer with OAuth, and calls are billed to your HireLayer plan. You can disconnect it by revoking its “(MCP)” key in Dashboard → API keys.

Which ChatGPT plans support it?

OpenAI documents custom MCP servers for Business, Enterprise and Edu, and read/fetch tools for Pro in developer mode. Check your workspace settings: an admin may have to allow custom servers.

Are the CVs I attach stored?

Like any API parse: the file is stored in Paris, France, and the parsed resume is saved to your HireLayer account. A workspace set with do_not_store_data keeps both out of storage. ChatGPT’s own data handling follows your OpenAI plan and settings.

Connect ChatGPT to HireLayer today

The Free plan includes 50 credits a month, no card required. Parsing a resume costs one credit, scoring one per resume evaluated, and extracting job criteria is free.