Claude organic app discovery just got turned on

Hey builders,

The biggest distribution shift since the ChatGPT App Store launched just. Claude is now surfacing Claude Connectors (MCP Apps) inside conversations at the exact moment a user expresses intent. No directory visit. No knowing your app exists. No installing anything ahead of time.

The user types what they want. Claude pulls in the apps that match. That's a brand new discovery field. It is a new form of SEO and every company will have to learn to optimise for it.

We're calling it ADO — Agentic Discovery Optimisation. Think SEO, but for optimising how agents use your tools. Full research paper coming soon.

People are very excited about it. We’ve been preparing for this moment for the last 6 months.

So today, we’re going to cover everything you need to know for this HUGE announcement:

• What happened

• Status of organic discovery and the Claude Connector ecosystem

• Ways you can organically appear in Claude

• How to optimise for it today

You can also read the full guide here.

What actually happened

For the last 6 months, Claude's connector ecosystem has been a you-have-to-know-it-exists world. You'd add a connector manually, search for one in the directory, or hear about it from someone else. Discovery was a brick wall.

That just changed.

Claude is now deciding - in real time, based on what you ask - which apps to surface. Sometimes as a list of options. Sometimes as part of a clarifying question. Sometimes pulled directly into the workflow as the default tool. Either way, your app either shows up or it doesn't, and the user makes a decision based on what Claude chose to put in front of them.

Importantly: this is not just happening for consumer apps, and this is not just happening for launch partners. We're seeing it across hotel booking, travel, presentations, document creation, research, finance, productivity — and the surface area is growing weekly.

You can read Claude's full announcement here.

Before we go deeper, one thing worth nailing down

When we say "apps in Claude," we're talking about connectors in the Claude directory - and connectors are MCP & MCP Apps.

The Model Context Protocol (MCP) is the open standard Anthropic, OpenAI, Microsoft and many others have all adopted to let LLMs call external tools and surface data and app experiences directly inside the conversation.

If you want to be discovered organically inside Claude, the prerequisite is simple: you need a Claude Connector (MCP / MCP App) live in the directory. Without one, you cannot get organically discovered as there is nothing for Claude to surface.

The good news: an MCP / MCP App you build for Claude is largely portable. With minor updates, the same app can be deployed into ChatGPT, Microsoft Copilot, and the other major LLM clients adopting MCP & MCP Apps. One build, multiple distribution channels.

If you don't have an MCP app yet, or you want one built well, Ghost Team builds production MCP & MCP Apps for enterprises. If you want to talk about building one or getting help with testing and distributing your MCP App, get in touch.

Where we actually are right now

Across the different AI Clients, discovery is in different stages of roll out. Here are the 3 states an app can be in inside any LLM client:

• Manual + named — user must install AND @mention the app every time

• Manual + organic invocation — user installs once, model decides when to call it (mobile-app era)

• Fully organic — user doesn't install or mention anything; the client surfaces the right app at the moment of intent

Where each major client sits today:

• ChatGPT (OpenAI) — connect required. Mention is sometimes optional. No fully-organic surfacing yet.

• Claude (Anthropic) — connect required for use, but organic surfacing is now live. This is the change.

• Microsoft Copilot — connect required. Organic surfacing is live and expanding.

Claude has just made a significant move. Until recently, Claude required you to have already connected an app for the model to invoke it organically. Now Claude is surfacing apps to users before connection - pulling them into the conversation as suggested tools the user can connect and use in a single click.

That's the change this whole post is about. Claude has moved a full step along the spectrum.

What the Claude Connector Ecosystem looks like today

We've been tracking every connector in the Claude directory daily since launch with our MCP App Intelligence platform. Here's what the data says as of April 24, 2026.

Connector growth over time

Claude opened the connectors directory in November 2025. In just under six months, the catalogue has grown to 353 live connectors.

April 2026 alone has already added more new connectors than any prior month - and we're only at the 24th. The pace is accelerating, not slowing.

Category breakdown

The catalogue isn't evenly distributed. A handful of categories dominate.

Claude is clearly leaning in on productivity and the B2B use case. Interestingly, in their announcement, they are now launching more B2C applications. I suspect this will continue and they'll try and take on more of the consumer market (and therefore, accept more consumer apps), further competing with OpenAI in this space.

The two ways organic discovery is showing up

We're seeing two distinct patterns. Both matter. Both are winnable.

Option 1 - Claude surfaces a shortlist of connectors

The user's intent maps cleanly to a category, and Claude returns a stack of relevant connectors with a Connect button next to each.

Example: hotel booking

User types "I want to book a hotel in London for tomorrow."

Claude responds: "A few good hotel booking options available. Which would you like to use?" Then it serves up:

• Booking.com — Find hotels, homes and more

• Tripadvisor — Find your perfect hotel based on Tripadvisor reviews

• Trivago — Find your ideal hotel at the best price

• DirectBooker — Compare hotels, then book direct

• Wyndham Hotels and Resorts — Discover the right Wyndham Hotel for you, faster

Five apps, one prompt. The user picks one. The other four don't get the conversion.

There are two things you have to win in a surface like this:

1. Are you on the list at all? This is the first cut. If Claude doesn't include you in the shortlist for this intent, nothing else matters - you weren't even an option the user could pick. Step one is making sure you're present for the prompts that matter to your business.

2. Where do you rank on the list? Once you're on it, position is everything. Top of the list will likely convert better than bottom - the same dynamic everyone learned with Google search rankings. Users skim, they pattern-match the first option that fits their intent, and they pick.

If you sell hotel bookings and you're not in that list, you didn't lose to a competitor on price or features - you lost because Claude didn't put you on the shortlist. And if you're on the list but ranked last, you stand less of a chance to get selected then whoever is at the top.

Option 2 - Claude surfaces apps inside clarifying prompts

This is the more subtle one.

When intent is broader (build a slide deck, write a doc, plan a trip), Claude asks clarifying questions - and the answer options themselves include specific apps.

Example: building a presentation

User types "I want to create a slide presentation."

Claude asks: "How polished does it need to be?"

Answer options:

1. Rough draft — just get ideas down

2. Client-ready — full design + content

3. Use Gamma (fast, themed)

4. PPTX file (editable in PowerPoint)

Gamma isn't competing with "another presentation tool" here. It's competing with file formats and abstract polish levels - and it's winning by being the named option the user can tap.

That's huge for any app placed there. Apps embedded into Claude's clarifying logic become the default path for people who select an app with that intent.

If you want early access to the full breakdown of which apps are being discovered, in which patterns, and for which prompts, sign up to AppDiscoverability.com and we'll be in touch.

The 3-step playbook to win it

Same loop we run for every enterprise on AppDiscoverability. There's no magic trick — there's a process.


→ 1. Measure rank + performance in-client.

The two factors that matter:

• Rank — do you appear for the prompts that matter, and where on the list?

• Performance — when called, does your app actually fire correctly and return what it should?

The questions you need to answer:

• Are you appearing for your target prompts, or is Claude surfacing a competitor?

• When you do appear, is it in Pattern 1 (the shortlist) or Pattern 2 (the named option in a clarifying flow)?

• Where do you rank — first, fourth, or buried at the bottom?

• What are competitors doing — taking your slots, gaining ground week over week?

• Are your tools actually firing without errors, timeouts, or silent failures?

Two things most teams get wrong:

• Local sims lie. We routinely see a 60% gap between local sim results and live in-client behaviour. System prompts, model routing, free vs. paid tier, geography, and competing tools loaded into the same conversation all change the outcome. None of that shows up in your server logs.

• Golden prompts lie too. Most teams test with perfectly phrased inputs that restate the tool name. Real users don't talk that way. We ran 5,000 prompts across 4 personas (golden user → vague non-technical user) and saw a 20-point drop in invocation rate end-to-end. Same intent. Wildly different outcomes.

→ 2. Optimize what agents choose. 

Once you have the data, work the levers. Every one of these moves rank:

• Tool name — how clearly it telegraphs purpose

• Tool description — specificity, "use this when…" framing, differentiation from neighbours

• App-level metadata — name, short description, long description, category placement

• Parameters & schemas — clarity, required vs. optional, examples

• Output structure — what the tool returns and how the model can chain off it

• Ratings, approvals, and real usage traction

Stanford research found nearly 100% of MCP tools have quality defects and roughly half don't clearly describe what they do. That's the gap. With real data in front of you, you can see exactly which prompts you're losing, which competitors are taking your placements, and which signal is dragging your rank down and fix the right thing instead of guessing at descriptions.

→ 3. Get discovered, then run the loop again. 

Discovery isn't static. Users change. Prompts change. Competitors change. Models change — sometimes daily. A description that ranks you #1 today can drop you off the shortlist entirely after a system prompt update on the client side.

The teams that win organic discovery treat it like SEO in 2008: a continuous loop. Measure → optimize → improve rank → measure again. Every week. Every model update. Every new competitor that lands in the directory.

We’ve been tracking this since day one

We've spent 6 months building the largest dataset on how organic discovery works inside Claude and ChatGPT.

AppDiscoverability.com's MCP App Intelligence platform tracks:

• 768 ChatGPT Apps - tracked daily, with full history reaching back to the launch of the ChatGPT App Store

• 353 Claude Connectors - every connector in the marketplace, monitored daily

• 532 new apps added in the last 30 days - the ecosystem is ramping up (ChatGPT App Store: 427 & Claude Connector Store: 105)

Every connector. Every touchpoint. Every ranking signal. Visibility scores, category breakdowns, growth over time, cross-platform presence - all of it.

If you don't have an MCP app live yet, that's the prerequisite - Claude can't surface what doesn't exist in the directory. Ghost Team builds production MCP apps for enterprises. One build, get it in every major LLM (ChatGPT, Claude, Copilot etc.)

Take action today

If you want to:

• See whether your app is surfacing for the prompts that matter

• Track your competitors and know when they overtake you

• Get the metadata, positioning, and ranking insights that move the needle

• Get notified when Claude changes how it ranks apps (because it will)

• Improve your organic discovery inside Claude for your target prompts

Sign up at AppDiscoverability.com - get better organic discoverability within Claude.

This is Day 1 of organic agent-driven distribution.

If you have any questions on how you can get ahead on the shift, drop me a reply here.

Happy building,

Elliot

If you want help building your MCP app or figuring out your cross-platform distribution strategy, book a strategy call with our team at Ghost Team.
We've been in this space since day one.