The product is on active development, such so that I can't announce every update, you can go check it out at doqment.dev/updates !
- New pricing, subscription
- New UI
- Better performance
- Soon to be released ChatGPT app
- More coming soon, as usage increases

Now agents with provided wallets can proactively pay per use their created MCP servers

Anyways, it took 3 steps: crawl documentation using http://doqment.dev -> attach to codex -> repeat until done.

On my app doqment.dev I noticed LLMs typically start using search_content tool in hopes for direct content referrals, so I just improved it!

Now it actually returns useful information, with citations, and suggestions out of just natural sentence queries. 
Here an example: 

Pretty surprised waking up to paying customers after investing time into making a tool to assist developers into better AI coding experiences, despite not "promoting while building" nor paying ads, just organic post-launch content.

Currently the app has just two digit users but 50% of them are paying customers

The app is doqment.dev (MCPs on demand). It emerged as an internal tool which turned into a product out of friends feedback, sort of like Claude Code

To give some stats out:

As first paying customers were acquired (50%) of active users, we rolled out an updates page to show the relevant work users must know about, plus all under the hood (performance, scalability, reliability work)
doqment.dev/updates

MCP it's turning out to be the clear standard, but the more we currently need

to wait for companies to deliver their action-first MCPs, the more we need

for a solution to not wait, and at least gather context for development process

instead of the good old copy-paste.
This is my proposal, spawn context aware MCP servers of resourceful sites,