Be the first to get access to new connectors. Get early access →
ConnectorBay Early access

Daybrief — Privacy Policy

Effective 22 September 2026. Unify Dynamics LLC ("we", "us"), Menlo Park, California.

What Daybrief is. Daybrief is a connector (an MCP server and REST API) that AI assistants and personal agents call on your behalf to summarise the news: headlines clustered across outlets, personal briefings, searches, timelines and background. You interact with your assistant; the assistant sends us only the specific request needed: a section, a topic, a list of interests or muted words, a place name, or a link you shared.

What we receive. The arguments of each tool call, 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.

What we do not receive or store. We do not receive your conversation with the assistant, your name, contacts, or account credentials for any service. We do not build a profile of your interests: interests and muted topics are used for the single request that carries them and are not stored. Tool inputs and outputs are processed in memory and are not stored. 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.

Links you share. For story_context, we fetch the first 120 KB of the page you shared to read its title and description tags, the way a link preview does. The request carries our own identifier, never yours. We do not store the page.

Sub-processors. To answer requests we forward the minimum necessary data (a topic, a query, a place name) to: - Publisher feeds (NPR, BBC, The New York Times, The Guardian, CBS News, NBC News, PBS NewsHour, Al Jazeera, CNN, The Washington Post, Politico, MarketWatch, Ars Technica, The Verge, TechCrunch, WIRED, MIT Technology Review, STAT, ScienceDaily, Nature, ESPN, CBS Sports, Variety) — we download their public RSS feeds; nothing about you is sent. - GDELT Project — a search phrase, for worldwide coverage and timelines. - Wikimedia Foundation — a topic name or date, for background and the current-events digest. - Hacker News (Y Combinator) — no data is sent; we read the public API. - Vercel — hosting infrastructure (United States regions).

Legal bases and your rights. For users in California, the EU/UK and elsewhere, 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 for advertising and do not use your data to train models.

Children. Daybrief is a general-audience service operated by the adult using the assistant.

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

Contact. Unify Dynamics LLC · agent@connectorbay.com