Claude
Example conversationFind a hotel near SFO with a free airport shuttle.
I can help you find a hotel. Connect a booking service to explore your options.
Turn your Claude Connector into a growth channel for your product. Track connector recommendations, compare competitors and review MCP changes that help Claude find and choose your product.
How often do agents surface your product for relevant requests?
Free to check. No account required.
“Working together we’ve gained insights into how this new frontier values, ranks, and ultimately recommends tools.”
Sanjay Vakil, PhD.CEO and Cofounder, DirectBookerOur agents monitor how Claude discovers your connector and prepare MCP improvements for your team to review.
See when agents organically surface your connector or plugin versus your competitors.
Illustrative dataPicked ÷ connector recommendations × 100. Each point is a rolling sample.
| Brand | Score | Position |
|---|---|---|
| 1 | 91 / 100 | 1.6 |
| 2 | 80 / 100 | 2.6 |
| 3 | 70 / 100 | 4.0 |
| 4 | 56 / 100 | 4.0 |
| 5 | 53 / 100 | 3.6 |
One recommendation can include multiple brands. Position is average shortlist rank; lower is better.
See which customer requests lead Claude to list your connector under “Connectors that could help”, and which competitors make the shortlist instead.
Find a hotel near SFO with a free airport shuttle.
I can help you find a hotel. Connect a booking service to explore your options.
Track when Claude mentions your product, lists your connector under “Connectors that could help” and which competitors share the shortlist, for the prompts you care about.
Find a hotel near SFO with a free airport shuttle.
DirectBooker can find hotels near SFO with a free airport shuttle and book directly with the hotel.
| Signal | Brand | Result |
|---|---|---|
1Brand mention | Mentioned | |
2Connector recommendation | Recommended · #1 | |
3Competitor connector | Also listed · #2 |
Run general discovery tests or create personas with memory in Claude. Compare when each persona finds your connector or a competitor’s.
Find a hotel near my meetings.
Where can I book rooms for our team?
Compare general discovery with persona context.
Compare your connector with competitors across prompts and personas. Follow changes to their MCP descriptions and tools.
Compare the description and capabilities.
Our agents draft improvements to your connector listing, tool names and descriptions. Review each change, approve what ships and measure the results in Claude.
Update the connector description with the project, task and status language agents use in relevant requests.
Manage projects, track tasks and share status updates.
Connect your product’s MCP and choose the customer needs and competitors to track.
See when agents overlook your product or choose a competitor.
Our agents investigate missed recommendations and draft improvements to your product’s MCP.
Update the tool description to match relevant customer requests.
Related discovery findingsReview draftReview each change, approve what ships and see how your product’s discovery results change.
Everything you need to know before you get started.
Read the methodologyIt monitors how Claude discovers your product through its connector. Our agents identify missed opportunities, prepare MCP improvements for your team to review and track discovery results after release.
Yes. For each tracked prompt, see whether your connector made Claude’s shortlist, its position and which competitors appeared alongside it.
Yes. Run general discovery tests in Claude or create personas with memory reflecting your target customers. Compare how your connector is discovered in different customer contexts.
MCP descriptions, tool descriptions and parameter guidance, plus new MCP tools that expose capabilities your product already supports. Each proposed change comes with supporting evidence and discovery tests to check its effect.
No. Changes go through your team’s review and release workflow. You control what is approved and shipped.
It measures how often your connector makes the shortlist in eligible Claude test conversations. It’s specific to the platform and prompts being measured. See the methodology for the full definition.