Job and requisition upkeep
Create and update the records behind openings, keeping the pipeline's structure matching the plan.
Pinpoint ATS connector
Pinpoint ATS MCP Connector – Candidates and Pipeline in One Question
Recruitment marketing spends real budget driving applicants, and then the funnel disappears into the ATS: applications somewhere, interview stages somewhere else, the "where are we on the designer role" answer living in whoever checked last.
The Pinpoint connector reopens the funnel. It links the AI you already use, like Claude, ChatGPT, or Copilot, to your Pinpoint instance through Mad Fish Elements, reading jobs, candidates, applications, interviews, requisitions, and org structure, plus the public job-postings feed, with the full JSON:API surface behind them. The hiring pipeline becomes as askable as the marketing one, because it is one.
See it
What Your AI Can See
Connect your instance, and your AI reads recruiting the way a funnel reads: the open jobs and their requisitions, the candidates in each, applications by stage, interviews scheduled and completed, and the org structure roles map into. The public postings feed reads too, so what the careers site advertises can be checked against what the ATS actually has open.
The standing questions become sentences. "Where are we on the designer role, stage by stage?" "Which openings have the fewest applicants after two weeks?" "How long are candidates sitting between application and first interview?" And for the teams spending money on hiring: the same Gateway reads the ad platforms, so "what did the job ads spend, and what did each source produce in applications?" joins recruitment marketing to its results in one pass.
Do it
What Your AI Can Do
With Write access and your approval, your AI maintains the recruiting records the process depends on:
Candidate and application management
Update records and stages where your flow calls for it, shown first, audited always.
Interview coordination support
Read and maintain the scheduling records, so "who is interviewing whom this week" is an answer, not an email chain.
Full API reach
The complete JSON:API surface routes through passthrough for whatever your instance models beyond the typed operations.
The honest line for a hiring system: records and stages are the connector's business; judgments are not. Screening decisions, offers, and everything a candidate would call a decision stay with the humans your process names.
A working session
The Monday Hiring Standup, Fed
In practiceThe session that changes recruiting rhythm: Monday, the brief arrives; open roles: nine, with stage-by-stage counts. Stalled: two roles with no candidate movement in ten days, flagged. Interviews this week: listed; the standup starts at the exceptions. Mid-meeting: "Which sources filled the last three engineering hires?" You ask; the funnel answers, source by source; the job-ads budget conversation that follows runs on evidence. Recruiting ops just started working like marketing ops, which was always the point of connecting it.
The return
What You Get Back
A visible pipeline
Every role, stage by stage, on demand and on schedule.
Stalls surfaced early
The role quietly going nowhere gets flagged in days, not discovered at the quarter review.
Recruitment marketing accountability
Job-ad spend beside the applications and hires it produced.
Careers-site truth
The public feed checked against the ATS, so closed roles stop advertising themselves.
Use cases
One Conversation, Real Account Work
"Show every open role with candidates by stage."Pinpoint ATS
The full funnel as a visual report.
"Which roles have had no candidate movement in ten days?"Pinpoint ATS
The stall report, flagged while fixable.
"What did we spend on job ads last month, and what did each source produce?"Pinpoint ATS · Google Ads · Meta
Recruitment marketing, closed-loop, in one pass.
"List this week's interviews with roles and interviewers."Pinpoint ATS
The coordination answer without the email chain.
"Does the careers feed match our actually-open requisitions?"Pinpoint ATS
The public-versus-internal parity check.
For in-house teams
Close the expectation gap
People teams get marketing-grade visibility into their own funnel, and the leaders asking "where are we on that role" get the answer without a meeting. The employer-brand budget finally reports like a budget.
For marketing teamsFor agencies
Run the whole book
Agencies hire constantly and recruit for clients occasionally; either way, the funnel becomes reportable. For recruitment-marketing engagements, spend-to-applications is the deliverable that wins renewals.
For agenciesReports worth sharing
From Live Account to Clear Story
Ask in chat and share the dashboard without building exports or taking screenshots.
Pipeline Board
Roles by stage, movement flagged. Built for the Monday standup.
Source Performance Report
Applications and hires by source, beside spend. Built for the job-ads budget.
Time-in-Stage Summary
Where candidates wait, by role. Built for fixing the slow spots candidates feel.
The charts do the talking: funnel for stages, bar for source comparison, line for time-in-stage trends. And when leadership wants these anytime, the Data Visualization add-on turns your reports into always-current dashboards they open from a link. Ask in chat; share the dashboard.
The useful signals
The Numbers That Matter
The hiring funnel reads like any funnel. Candidates by stage, per role: the pipeline snapshot. Movement: which roles advanced candidates this week, and which sat still. Time in stage: where candidates wait, and how long, the number they feel most. Applications by source, beside spend: recruitment marketing, held accountable. And careers-feed parity: whether the public site matches the actually-open roles. Read the pipeline weekly, sources monthly, parity whenever roles open or close. Stalls are the killer in hiring; a role that sat still for two weeks lost its best candidates to someone who moved. The Monday board exists to make sitting still visible in days.
A practical start
Your First Week
Day one: connect the instance and see the funnel. "Every open role, candidates by stage." Day two: find the stalls. "Roles with no movement in ten days." Day three: check the public story. "Does the careers feed match our open requisitions?" Close anything advertising a filled role. Day four: close the marketing loop. "Job-ad spend last month against applications by source." Day five: schedule the standup feed. "Monday mornings, send the pipeline board." By Friday, recruiting has what marketing has had all along: a visible funnel, flagged stalls, and spend that answers for itself. The hiring questions leadership asks in hallways now have standing answers, and the standup starts at the exceptions instead of the inventory.
Works best with
Build the Connected View
Pair Pinpoint with Google Ads and Meta where job ads run, closing the recruitment-marketing loop. Add Rippling for the hire-to-headcount handoff, inside its gates. Hiring is a funnel; funnels report best beside their spend.
A note on why this pairing matters; hiring is the one funnel most companies never instrument. Marketing measures everything; recruiting measures offers made. The gap costs real money: job ads with no source data, roles that stall unseen, candidates lost to slow stages nobody timed. Close the gap the same way marketing did; read the funnel weekly; put spend beside results. Fix the slowest stage first; the tools were always there; now the reading is too.
Clear limits
What This Connector Will Not Do
It will not screen, rank, or reject candidates; people decisions stay with people, full stop. It will not message applicants; communication runs through your process in Pinpoint. It will not expose candidate data beyond your permissions, and access here should be scoped to the recruiting team and the leaders who need pipeline visibility. And it will not touch instances you did not connect.
Governance
Governed Access Your Whole Org Can Live With
Access is set per person, not per account, so Read seats see everything and change nothing while Write seats create and edit with your approval flow in front of every change. Delete access goes only to people you trust to clean up, and many teams start read-only, check answers against the platform, then widen access as the audit trail earns it.
You choose the level of human review and can change it at any time, while every action records what changed, when, and who approved it. Per-user access means Elements never stores your Pinpoint ATS password, and your data is never harvested or resold.
Per-user accessRead / write / delete per seatFull audit trailApproval flow on every change
Setup
Setup Takes Minutes
- Start your trialCreate your Elements account and connect it to your AI.
- Link Pinpoint ATSSign in through the secure connection screen and choose what to connect. No code and no engineers.
- Set permissionsDecide who can Read, who can Write, and who can Delete. Start conservative and widen as trust builds.
- Ask your first question"How did we do last month?" is a complete instruction.
Plans, account limits, and the multi-client Agency plan are on the pricing page .
FAQ
Pinpoint ATS Connector Questions
Is this appropriate for candidate data?
It reads what your instance authorizes, for the Elements users you permit, with the audit trail recording access to changes. Scope this connector to recruiting staff and pipeline-level reporting for leaders; per-person permissions make the narrow shape easy.
Does it make any hiring decisions?
No, and it is built not to. Records, stages, schedules, and reporting are its surface; evaluation and decisions are yours.
What is the job-postings feed for?
It is Pinpoint's public careers feed. Reading it lets your AI verify the public site against internal reality, and gives marketing the live list when careers content needs it.
Will my AI change things without asking me?
No. Your AI acts only with the permissions you set, and changes follow the review level you choose. Read-only seats cannot change anything, because the approval flow is the product working as designed.
Which AI assistants can our team use?
Your team can use Claude, ChatGPT, and Microsoft Copilot, while other AI tools can likely connect when they support MCP, the open standard for linking AI assistants to outside tools.
Is my data used to train anything?
No. Your data stays yours, so nothing is harvested and nothing is resold.
Focus on the Strategy, Delegate the Launch
The teams winning with AI are not handing their accounts to a black box; they keep the strategy and delegate the hands-on-keyboard work, while approvals and an audit trail make it safe to move fast. Connect the account you already have through the Gateway and ask the question you would normally build a report to answer.
Your first 14 days are free. Add your card to start, and cancel before the trial ends to pay nothing.