Flag Check

What Flag Check is for

"What do people actually mean by a relationship 'red flag'?" — a fully local, EDUCATIONAL reference on widely- discussed relationship-health patterns, written to inform reflection, never to diagnose.

What it does

flag_info gives one named pattern's description and the general educational framing behind it — why relationship educators point to it — across six categories: communication, respect, boundaries, trust, conflict resolution, and support. flag_search finds patterns by keyword; flags_by_category lists everything in one category, optionally narrowed to green flags, red flags, or context-dependent ones; category_list shows all six with counts. context_dependent_flags covers patterns that depend heavily on context rather than being simply good or bad — like very intense early affection, where the pace matters more than the warmth itself. self_reflection_prompts gives open-ended, non-diagnostic journaling questions by category, meant to sit with rather than "score." relationship_glossary defines commonly-discussed terms — gaslighting, love bombing, stonewalling, attachment style, codependency — in general, educational language. compare_flags lines up a few named patterns side by side. when_to_seek_support gives resource-oriented guidance on bringing in a trusted person, a licensed counselor, or a helpline for anything serious.

What it is not

Not a diagnostic tool, a relationship test, or a substitute for a licensed counselor or therapist. It never tells anyone that their relationship is healthy, unhealthy, or abusive — only the person living it has the full context to make that judgment, ideally with support from people who know them. Every pattern here is general and widely discussed by relationship educators; this reference exists to inform reflection and conversation, and it consistently points toward trusting your own judgment and seeking real support — a trusted person, a licensed counselor, or a local helpline — for anything serious rather than treating this tool as the last word.

Flag Check — Privacy Policy

Effective 26 September 2026. Unify Dynamics LLC ("we", "us"), Menlo Park, California.

What Flag Check is. Flag Check is a connector (an MCP server and REST API) that AI assistants and personal agents call on your behalf for a fully local, educational relationship-pattern reference — pattern descriptions, category browsing, self-reflection prompts, a glossary, and resource guidance. You interact with your assistant; the assistant sends us only the arguments needed for that one lookup.

What we receive. The arguments of each tool call — a pattern name, a category, a search keyword, or a topic for reflection prompts — 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.

Everything is answered from bundled, hand-curated content and nothing is stored. No request is forwarded to any third party — there is no upstream call at all, live or otherwise — and no query is logged in request bodies, recorded, or used to train anything. This is especially deliberate here: we understand that queries to this connector may be personal, and we have built it so there is nothing to store or retain in the first place.

What we do not receive or store. We do not receive your conversation with the assistant, your name, or any detail about your relationship or the person you're asking about — the tool only ever sees a generic pattern name or category. Each request is answered independently and nothing carries over between requests. Rate-limit counters (a client identifier and timestamps) 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 — the entire content bank is bundled with the server and answered locally. 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 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. Flag Check is a general-audience service operated by the adult using the assistant.

If you're in crisis. This Service is educational only and is not equipped to respond to a safety emergency. If you are in immediate danger, contact local emergency services. For non-emergency support, a licensed counselor, a trusted person in your life, or a local domestic-violence or crisis helpline can help in ways this reference cannot.

Changes. We will post changes here with a new effective date.

Flag Check — Terms of Service

Effective 26 September 2026. These terms govern use of the Flag Check connector ("the Service") operated by Unify Dynamics LLC ("we", "us").

1. The Service. Flag Check returns a fully local, educational reference on general, widely-discussed relationship-health patterns across communication, respect, boundaries, trust, conflict resolution and support. It is accessed through an AI assistant or directly over MCP or HTTP.
2. Educational only — not a diagnosis, not therapy, not legal advice. Flag Check is a general-education reference, not a mental-health, medical, legal, or diagnostic service, and not a substitute for a licensed counselor or therapist. No content in this Service should be understood as a diagnosis or clinical evaluation of any real relationship or person. Every pattern described is general and widely discussed; whether it applies to a specific real-world situation is a judgment only the people involved — ideally with professional support for anything serious — can make.
3. Not an emergency or crisis service. This Service cannot assess risk or respond to a safety emergency. If you or someone else is in immediate danger, contact local emergency services. For non-emergency support, contact a licensed counselor, a trusted person, or a local domestic-violence or crisis helpline.
4. Reference content, not real-time guidance. Content reflects general, widely-discussed relationship-education concepts as of the build date stated in the Service's own data. It does not know the specific people, history, or circumstances of your situation.
5. Acceptable use. Automated use within the published rate limits is welcome. Do not use this Service, or any output from it, to harass, stalk, or make unilateral accusations against another person.
6. Availability. The Service is provided "as is" without warranty. We may change, limit or discontinue it at any time.
7. Data. Our Privacy Policy describes what we process. In short: your query is answered from bundled content, and nothing is stored.
8. Pro keys. Optional Pro API keys are issued at our discretion, are personal to the holder and may be revoked for abuse.
9. Liability. To the fullest extent permitted by law, Unify Dynamics LLC is not liable for any loss, injury, or damage arising from use of, or reliance on, the Service — including any decision made about a relationship based on its content. Our total liability is limited to US $100.
10. Governing law. California law; venue in San Mateo County, California.
11. Contact. Unify Dynamics LLC · agent@connectorbay.com · https://connectorbay.com/flagcheck

Flag Check support

Email agent@connectorbay.com. We answer within two business days.

• MCP endpoint: https://flagcheck.connectorbay.com/mcp
• REST API: https://flagcheck.connectorbay.com/openapi.json
• Live status: https://flagcheck.connectorbay.com/health

When 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. Flag Check never asks for them.