Integration · Payroll & HR

Connect Claude & ChatGPT to HrFlow.ai

Ask your AI which candidates fit a job, how a profile scores, or to pull structured data out of a CV text in HrFlow.ai. It can search, grade, score and match profiles and jobs across your sources and boards, explain a match, and index new profiles and jobs. It can also parse, tag and geocode text and manage your taxonomies and tags.

Connect HrFlow.ai free

Free plan, no credit card. Takes about a minute.

Try asking

“Which profiles in our Applicants source fit the Senior Data Engineer job best?”
It grades the profiles in the source against the job and returns them with their grades.
“Find jobs on our Careers board that are close to the Backend Developer role.”
It matches the jobs indexed in the board to the job you name and lists the closest ones.
“Explain why Anna Larsen's profile fits the Product Manager job.”
It asks HrFlow.ai to explain the profile for that job and returns the explanation.

What your AI can do

Search and matching

Search profiles and jobs by name, reference or location, and match profiles to profiles or jobs to jobs.

Scoring and explanations

Score and grade profiles against jobs, explain a profile for a job, ask questions to a profile or job, and unfold a career path.

Indexing, text and taxonomies

Index and archive profiles and jobs, parse, tag, embed and geocode text, and manage taxonomies, tags, ratings and trackings.

“Parse this CV text and show me the skills and experience.”
It sends the text to HrFlow.ai's text parser and returns the structured result.
“Does this candidate have experience with Python?”
It asks the question to the profile indexed in your source and returns HrFlow.ai's answer.
“Add the Warehouse Lead job posting to the Careers board.”
It indexes the job in the board, so it can be searched, scored and matched from then on.

21 tools for HrFlow.ai

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

add_jobChanges dataAdd a job to a Board. Pass the full job object in `job` and the board_key.
add_profileChanges dataAdd a candidate profile to a Source. Pass the full profile object in `profile` and the source_key.
ask_job_questionAsk questions in plain language about a job, e.g. 'Is this role remote?'. Needs board_key, the job's reference and `questions`.
ask_profile_questionAsk questions in plain language about a candidate profile, e.g. 'How many years of Python experience?'. Needs source_key, the profile's reference and `questions`.
explain_job_fitExplain why a job is recommended to a candidate. Needs source_key, profile_key, board_key and job_key; optional score and output_lang.
explain_profile_fitExplain in plain language why a candidate fits a job, with strengths and gaps. Needs board_key, job_key, source_key, profile_key and the match score (0-1).
get_jobGet one job from a Board by board_key and the job's reference.
get_profileGet one candidate profile from a Source by source_key and the profile's reference.
get_resume_parsingGet the parsed result of a resume stored in a Source, by source_key and the profile's reference.
list_boardsFind the Boards (job databases) in your workspace, optionally by name. Most job tools need a board key from here.
list_ratingsList ratings given to candidates or jobs. Needs role; filter by source or board keys, profile or job.
list_sourcesFind the Sources (profile/candidate databases) in your workspace, optionally by name. Most profile tools need a source key from here.
list_trackingsList recorded stages/actions for candidates or jobs. Needs role; filter by actions, source or board keys, profile or job.
parse_textChanges dataParse raw text (a resume, job ad or profile) into structured data with AI. Pass `texts` and parsing_model (quicksilver for speed, atlas for accuracy); output_object picks text, job or profile.
rate_profileChanges dataRate how well a candidate fits a job, with a score from 0 to 1 and an optional comment. Needs role, score, board_key and source_key, plus the job and profile keys or references.
score_jobs_for_profileRank the jobs in given Boards (board_keys) for one candidate, using a scoring algorithm. Needs algorithm_key, source_key and the profile's key or reference.
score_profiles_for_jobRank the candidates in given Sources (source_keys) for one job, using a scoring algorithm. Needs algorithm_key, board_key and the job's key or reference; filter by stage, skills and more.
search_jobsSearch jobs in one or more Boards (board_keys). Filter by names, skills, languages, tags and more. Results are paginated.
search_profilesSearch candidate profiles in one or more Sources (source_keys). Filter by name, email, stage (new, yes, later, no), skills, languages and more. Results are paginated.
track_profile_stageChanges dataRecord a stage or action for a candidate on a job, e.g. moving them to an interview stage. Needs role (recruiter, candidate, employee, manager), action, board_key and source_key, plus the job and profile keys or references.
update_jobVisible to othersUpdate a job already in a Board. Pass the edited job object in `job` (including its key) and the board_key.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose HrFlow.ai from the app list.
2
Paste your key
Paste your HrFlow.ai API key and the email of your HrFlow.ai user into their own fields. Sign in to your HrFlow.ai workspace and copy the API key from the workspace's API key settings. Some tools need a key with write permissions.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in HrFlow.ai?

The AI can read your sources, boards and workflows, search profiles and jobs, and score, grade and match them. It can explain a profile for a job, ask questions to profiles and jobs, and parse, tag, embed and geocode text. It can also index, edit and archive profiles and jobs, and manage taxonomies, tags, ratings and trackings.

Does the AI see my HrFlow.ai API key?

No. Your HrFlow.ai credentials are encrypted at rest and never shown to the AI. After you save them, they are not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start with search and scoring only. Archiving a profile or job and deleting a taxonomy or tag can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own HrFlow.ai workspace.

Why does HrFlow.ai need an email as well as the API key?

HrFlow.ai identifies API calls with two values: your workspace API key and the email of your HrFlow.ai user. You paste both into their own fields in PipMCP. If a write tool such as indexing is refused, check that your key has write permissions.