For AI users
Ask an assistant about me instead of reading all this.
If you already work in Claude or Codex, you can connect my business to it. In the ChatGPT desktop app, select Codex to use this connection. Your assistant then has my case studies, my prices, my writing and what I’m and am not good for, and you can interrogate all of it in your own words. I never see the conversation. The questions your assistant sends my server are answered and not stored, and the privacy page says exactly what reaches me.
The address to paste
https://www.ashleypayne.co.uk/mcp
Read-only, and there’s nothing to sign in to. It serves the same things this website says.
Setup
Connecting it
Connect it in Claude, or use Codex in the ChatGPT desktop app. Follow the steps for the conversation you want to use.
Claude
- Open settings and go to Connectors.
- Choose Add custom connector.
- Name it Ashley Payne and paste the address above.
- It will say it can’t check the server, or can’t work out how the server signs in. That’s expected here, because there’s nothing to sign in to. Choose Continue anyway.
- Turn it on in a chat from the tools or + menu.
Works on Free, Pro, Max, Team and Enterprise, though Free is limited to one custom connector. No developer settings needed.
Codex in ChatGPT desktop
- Open the desktop app. In the ChatGPT dropdown, select Codex.
- Open Settings, then MCP servers and Add server. In versions with a Plugins menu, choose Add, then Add MCP server.
- Name it ashley_payne, choose Streamable HTTP and paste the address above as the URL.
- Leave the bearer token and header fields empty. There’s nothing to sign in to.
- Save, then select Restart.
- Start a new Codex chat and choose Local.
- Type /mcp and check that ashley_payne is connected. Then ask your question.
These steps connect Codex running locally in the ChatGPT desktop app. Adding this server does not make it available in ordinary ChatGPT chats or in the browser. The Codex CLI and IDE extension can use the same connection on this computer.
Worth asking
Ask it the questions you wouldn’t ask me.
It will tell you when I’m the wrong choice, because I built it to. Where the wording is unclear it doesn’t guess: it hands your assistant three plain questions, and the rule that turns your answers into a yes or a no is mine, published, and the same for everyone who asks. Your assistant carries the answers. It doesn’t get to decide what they mean.
- Is Ashley the right fit for what I’m building?
- What would working with him cost?
- Has he built anything like my problem before?
- How does he decide whether AI is the right answer?
- What would he tell me not to do?
If it says I’m not a fit, that’s worth taking seriously and it isn’t the last word. It only knows what your assistant passed on, and I can’t see whether that came from you or from something it inferred. If the answer surprises you, tell me what it said and I’ll give you the real one.
Why this exists
I build these for a living.
Businesses are finding that their staff use AI assistants all day with no access to company context, so the assistant invents one. I build MCP servers over real systems to fix that, and this site runs on the same thing I’d build for you.
If you’d rather see it applied to a business than to a CV, the coding education case study covers the same pattern over live booking and pipeline data.
Work with me
Rather just have a conversation?
The assistant is for people who prefer it. Everyone else can email me.