Lucca (BYOK)
Read your Lucca HR directory (employees, departments, establishments, legal units) and office work locations with your own API key
Exit-interview question bank, structure guide, and a real theme aggregator across departures
Unify Dynamics LLC
Real questions, and the tools your agent calls to answer them.
exit_interview_question_bankexit_interview_structure_guideexit_theme_extraction_methodologyexit_theme_aggregatorExitinterview is a fully local exit-interview toolkit. exit_interview_question_bank is a hand-curated bank across five categories: reason for leaving, manager/team feedback, what would have made them stay, company-culture feedback, and whether they'd recommend the company. exit_interview_structure_guide covers in-person vs written-survey tradeoffs, who should conduct it (explicitly not the departing employee's direct manager, for candor), timing, and confidentiality framing. exit_theme_extraction_methodology explains how to aggregate exit-interview data across many departures to spot real patterns: minimum sample size, coding open text into categories, and weighting/grouping by team and time window. exit_theme_aggregator actually performs that aggregation: given a list of exit-interview records (primary reason category, optional would_recommend, optional culture_rating), it computes the real frequency distribution of reasons, percent who'd recommend, and average culture rating, explicitly flagging samples under 4 records as insufficient for a trend. Keyless; fully local; nothing submitted is stored or logged.
Sources: Computed locally / hand-curated exit-interview reference; fully local, zero upstream calls
The publisher, Unify Dynamics LLC, states that tool inputs are processed in memory and not retained.
4 tools, grouped by job. Every one is read-only or compute-only.
https://exitinterview.connectorbay.com/mcpRead your Lucca HR directory (employees, departments, establishments, legal units) and office work locations with your own API key
Read employees, groups, locations, time off and ATS jobs from the HR or recruiting systems connected to your Unified account, with your own key (no pay, ID or birth data)
Read departments, locations, holidays, labels, leave types, leave requests, users and leave balances from your Vacation Tracker workspace with your own API key
Read leave types, leave balances, pay periods, termination reasons, departments and ATS reasons and tags from the HR system linked to your Knit account, with your own keys
Read teams, locations, absence types, time off balances and ATS stages from the HR system linked to your Kombo account, with your own keys
Read jobs, candidates, applications, interviews, stages and offices from the applicant tracking system linked to your Merge account, with your own keys (no contact, offer or diversity data)
Most exit-interview advice stops at "ask good questions." Exitinterview also covers the two things that actually determine whether the answers are honest and useful: who's in the room, and how you turn a pile of individual conversations into a real signal instead of reacting to whoever complained most recently.
exit_interview_question_bank is a hand-curated bank across five categories: reason for leaving, manager/
team feedback, what would have made them stay, company-culture feedback, and whether they'd recommend the
company. exit_interview_structure_guide covers the format decisions that affect data quality — in-person/
video versus a written survey (candor and follow-up tradeoffs in each direction), who should actually conduct
it (explicitly not the departing employee's own direct manager, since candor about a manager or team collapses
when that manager is in the room), timing (last week versus after departure), and confidentiality framing.
exit_theme_extraction_methodology explains HOW to turn many exit interviews into a real pattern: a minimum-
sample-size rule of thumb, coding open-text reasons into a fixed category set with inter-rater checking, and
weighting/grouping by team and time window. exit_theme_aggregator actually does that aggregation: give it a
list of exit-interview records (a primary reason category, optionally whether they'd recommend the company,
optionally a culture rating) and it computes the real frequency distribution of reasons, the percentage who'd
recommend the company, and the average culture rating — and explicitly flags the result as an insufficient
sample below four records, so a single departure's story is never presented as if it were a trend.
Not a substitute for actually reading the open-ended answers, and not HR or employment-law advice. The aggregator computes real statistics over the categories and ratings you supply, but coding a nuanced, open-text reason into one primary category necessarily loses detail — treat the aggregate as a starting point for investigation, not the final word, and always read a sample of the actual responses behind any number here before acting on it.
Effective 28 September 2026. Unify Dynamics LLC ("we", "us"), Menlo Park, California.
What Exitinterview is. Exitinterview is a connector (an MCP server and REST API) that AI assistants and personal agents call on your behalf for exit-interview question banks, structure guidance, and theme aggregation across exit-interview records. You interact with your assistant; the assistant sends us only the arguments needed for that one tool call.
What we receive. The arguments of each tool call — which may include a category name, or a list of exit- interview records (a primary reason category, an optional would-recommend flag, and an optional culture rating — no names or other identifying details are required by any tool) — the technical headers needed to serve the request (an IP address or a client identifier supplied by the assistant, and a Pro API key if you have one), and standard server logs.
We do not store, log, or retain the records you submit. Every tool computes on the data you send in memory, for that one request, and returns a result — nothing about a specific departure, an employee, or an aggregated result is written to a database, written to a request log, cached, or used to train anything. Request bodies are not logged.
What we do not receive or store. We do not receive your conversation with the assistant, and we do not build a profile from your queries: each request is answered independently and nothing carries over between requests. Rate-limit counters (a client identifier and timestamps, never the request content) are held in memory for at most 24 hours. Hosting-provider access logs, which contain IP addresses and request paths but not request bodies, are retained for up to 30 days for security and abuse prevention.
Sub-processors. None — there is no upstream call at all; every tool either computes on your submitted records locally or reads from a reference table bundled with the server. Hosting: Vercel (United States regions).
Legal bases and your rights. Our processing is necessary to provide the service you request through your assistant. Because we store no personal data beyond short-lived, content-free logs, requests to access, correct or delete personal data are usually satisfied automatically; you can still contact agent@connectorbay.com and we will respond within 30 days. We do not sell or share personal information and do not use your data to train models.
Children. Exitinterview is a general-audience service operated by the adult using the assistant.
Changes. We will post changes here with a new effective date.
Effective 28 September 2026. These terms govern use of the Exitinterview connector ("the Service") operated by Unify Dynamics LLC ("we", "us").
Email agent@connectorbay.com. We answer within two business days.
https://exitinterview.connectorbay.com/mcphttps://exitinterview.connectorbay.com/openapi.jsonWhen you report a problem, include the question you asked your agent, roughly when, and which agent you used (for example Claude, ChatGPT or Gemini). Never send us passwords, account numbers or ID numbers. Exitinterview never asks for them.