6 posts tagged with "ChatGPT"

TL;DR​

• ChatGPT Ads are sponsored chat_card units below ChatGPT answers, labeled "Sponsored" and visually separate from the model's reply. They reach Free and Go users in supported regions; Plus, Pro, Business, Enterprise, and Education do not see ads (OpenAI Help Center). OpenAI expanded self-serve beyond the US test to the UK, Mexico, Brazil, Japan, and South Korea on August 11, 2026 (Testing ads in ChatGPT).
• Early public data (third-party, US-heavy, July 2026): SE Ranking sampled 50,006 commercial prompts and saw ads on ~26%; their own spend test reported ~97k impressions, ~1,263 clicks, and ~1.3% CTR with weak downstream sign-ups. Sensor Tower estimates put active advertisers at ~300 in April → 820+ in July. Treat as directional — not industry benchmarks.
• Targeting is conversational, not keyword-based: you write context hints on ad groups describing the chats where your offer fits. There is no keyword volume or pre-flight CPC forecast; you plan with budgets and post-delivery insights instead.
• Account setup runs through Ads Manager Beta — business onboarding, Persona verification, billing, manual review, then Settings → API Keys for MCP. Campaigns won't deliver until account info (name + logo) and review finish (Account Setup help).
• The OpenAI Ads MCP server on MCPBundles wraps the API for Claude, Cursor, and other agents: account overview, context-hint and copy audits, paused campaigns, geo lookup, creative upload, conversion setup, and delivery reads from chat.

You're evaluating a channel that barely existed in paid media a year ago. ChatGPT Ads started as a US test in early 2026 and is still rolling out market by market.

Northbridge Legal runs Google Search for intake keywords and wants a second line on ChatGPT without another console tab for every standup. Their marketer's first question isn't "where's the button?" — it's whether yesterday's test bought anything worth keeping, and whether the account is still stuck in review.

Worth knowing what you're buying before you touch budget. Also worth knowing what you're not buying (keyword volume, chat transcripts, pre-flight CPC quotes).

The next shift in AI tools is not only smarter text. It is AI you can see — maps, layouts, and lists that show up inside the conversation when a paragraph is not enough.

MCP Apps (the official extension for interactive UI in MCP hosts) are still early. Iframes feel clunky on some hosts, CSP trips up builders, and Claude and ChatGPT do not behave identically. When it works, though, the conversation changes: you get something you can click, drag, or approve — not just read.

Below are three real screenshots from ChatGPT — Canva, Tripadvisor, and Charge Atlas. No stock art, no protocol demo tiles.

Every Model Context Protocol server on the internet is, at the end of the day, a URL. The hard question is which AI tool you're going to plug it into — and the honest answer is that the experience varies wildly depending on which app you live in.

I run MCPBundles, so I see what users actually do after they generate an MCP URL. A lot of them sign up, get the URL, then bounce because the next step — wiring it into the tool they actually use — is unfamiliar territory. Sometimes that's our fault for not making it obvious. Sometimes the tool's setup flow is genuinely awkward. And sometimes the tool literally hides MCP behind a developer toggle that nobody told you to flip.

This is the field report I'd write a friend who asked me, today, "which AI tool should I use if I want MCP to actually work?" Frank, opinionated, with the quirks named.

MCP Apps look simple in the spec. Your tool returns HTML, the host renders it in an iframe, the user sees a dashboard instead of a wall of JSON. Build one app, it works everywhere.

In practice, I've shipped MCP Apps to both ChatGPT and Claude over the past few months and learned that "works everywhere" requires handling a surprising number of sharp edges — iframe sandboxing, data format differences, a picky initialization handshake, and an interactive tool-calling pattern that's barely documented anywhere.

Here's everything I've learned, with the exact code for each one.

When OpenAI integrated support for Anthropic's Model Context Protocol (MCP) into ChatGPT's deep research feature, they documented something elegant: a two-tool pattern that gives AI agents a consistent way to engage with any data source. If your MCP server implements search and fetch with their specific signatures, ChatGPT knows exactly how to explore your data without custom integration code.

Both tools accept only a single string parameter. That constraint isn't a limitation—it's what makes the pattern universal.

OpenAI just made it clear: if you want your MCP server to work with ChatGPT's deep research capabilities, it needs to implement two specific tools: search and fetch.

This isn't optional. It's the protocol standard that enables ChatGPT to discover and retrieve information from external data sources. And if you're using MCPBundles, you already have it.