Ashley Payne, technical co-founder and fractional CTO

uk.co.ashleypayne由 ashleypayne.co.uk 发布官方发布者v1.0.1更新于 Oct 24, 2026

Ask a UK fractional CTO's practice directly: services, prices, articles, and whether he fits.

已验证Streamable HTTP可网页运行知识与记忆商业与电商

概览

AI 生成的概览

一个远程只读连接器,接入英国兼职 CTO 的业务资料,可回答服务、价格、案例、文章以及项目是否合适等问题。

可以做什么
阅读业务概览、服务、价格和合作方式,以及 AI 能力和对数据隐私、自动化问题的看法。根据描述的项目获得匹配结论,并在公开规则需要时返回待回答的问题。浏览案例摘要并查看完整案例,包括技术栈和工程决策。搜索文章并阅读全文,查询潜在客户的常见问题。获取联系方式与预约信息、网站数字的来源说明,以及该连接器的隐私声明。
适用场景
在评估 Ashley Payne 作为兼职 CTO 或技术联合创始人时适用,可在对话中直接获取其公开资料中的答案,包括联系前的初步匹配判断。
运行要求
远程 Streamable HTTP 端点,无需本地安装或运行。无需身份验证、API 密钥、请求头或账户。任何支持 Streamable HTTP 的客户端均可连接。
安装前请注意
所有工具均为只读,参数不会被记录,但 README 建议不要在匹配检查中填写个人或机密信息。公开数字为自行报告,未经独立审计。匹配结论仅供参考,依据固定的公开规则得出。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Ashley Payne, technical co-founder and fractional CTO,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/uk.co.ashleypayne%2Fashley-payne/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "ashley-payne-technical-co-founder-and-fr": {
      "type": "http",
      "url": "https://www.ashleypayne.co.uk/mcp"
    }
  }
}

README

Ashley Payne MCP server

A remote, read-only MCP server for the practice of Ashley Payne, a UK technical co-founder and fractional CTO. Connect it to your assistant and ask about his services, how an engagement runs and what it costs, his case studies and articles, and whether he suits your project.

  • Endpoint: https://www.ashleypayne.co.uk/mcp
  • Transport: Streamable HTTP
  • Authentication: none
  • Registry name: uk.co.ashleypayne/ashley-payne
  • Documentation: https://www.ashleypayne.co.uk/ai

This repository holds the description and configuration only. The server is hosted, and the hosted endpoint is the product, so there's nothing to install or run.

What it does

It answers from the same published content as ashleypayne.co.uk, so the assistant and the website can't disagree.

The fit checker is the part that's a tool rather than a brochure. Describe your situation and it returns a verdict: good_fit, mixed, poor_fit or insufficient_information. The rule that produces the verdict lives on the server and is the same for everyone. Your wording on its own never produces a no. If something you wrote raises a question (do you want him to supply a delivery team, for instance), it comes back as a question for you to answer, and only a confirmed answer changes the verdict.

Tools

ToolWhat it returns
get_overviewThe first call: who he is, his background and what sets him apart.
assess_fitA verdict on whether he suits your project, with any questions to answer first.
get_servicesServices, prices and how an engagement runs.
list_workThe case studies, with clients unnamed.
get_case_studyOne case study in full.
get_ai_capabilityHow he approaches AI work, including when it isn't the answer.
search_insightsSearch his articles.
get_insightOne article in full.
get_faqsThe questions buyers ask, with answers.
get_contactEmail and the booking link.
get_evidenceHow the figures on the site are counted.
get_privacyWhat happens to what you send the server.

Prompts

is_he_right_for_me, what_would_this_cost, compare_my_options and check_the_evidence start the common conversations for you.

Configure it

Claude (web and desktop)

  1. Open Settings, then Connectors.
  2. Choose Add custom connector.
  3. Name it Ashley Payne and paste https://www.ashleypayne.co.uk/mcp.
  4. If it says it can't work out how the server signs in, choose Continue anyway. There's nothing to sign in to.
  5. Turn it on in a chat from the tools or + menu.

Claude Code

claude mcp add --transport http ashley-payne https://www.ashleypayne.co.uk/mcp

VS Code with GitHub Copilot

Add this to .vscode/mcp.json in your workspace, or to your user MCP configuration:

json
{  "servers": {    "ashley-payne": {      "type": "http",      "url": "https://www.ashleypayne.co.uk/mcp"    }  }}

Codex in the ChatGPT desktop app

Open Settings, then MCP servers, and add a Streamable HTTP server named ashley_payne with the endpoint above as its URL. Leave the token and header fields empty, save and restart, then start a new Local Codex chat and type /mcp to check it's connected. This connects Codex running locally; it doesn't make the server available in ordinary ChatGPT chats.

Anything else

Any client that speaks Streamable HTTP can connect to the endpoint directly. There's no API key, header or account.

Use it

Ask in your own words. For example:

  • "Who is Ashley Payne?"
  • "What does he charge, and how does an engagement work?"
  • "Has he built anything like our problem before?"
  • "How does he decide whether AI is the right answer?"
  • "We have developers already. We need one accountable fractional CTO to set direction. Is he a fit?"

The last one will come back with a few questions first. Answer them and ask again.

Privacy

Every tool is read-only. There's no sign-in, no session and no database, and tool arguments aren't logged. Keep personal and confidential details out of the fit checker, because the shape of the problem is enough. The full notice is on the privacy page, in the section on the AI connector.

Contact

Built and run by Ashley Payne Systems Ltd, registered in England and Wales, company number 17463066. [email protected]

来源:README.md,提交 f0c41fd

工具

12

get_overview

Who Ashley Payne is

Positioning, background and what makes him different from other fractional CTOs. Start here.

无需输入参数。

assess_fit

Check whether he suits your project

Compares a description of a project, business or problem against a fixed published rule and returns a verdict: good_fit, mixed, poor_fit or insufficient_information. Wording alone never produces poor_fit. Where the text touches one of the things Ashley turns down, the result lists questions in ask_these_then_call_again, and the three named fields take the person's own answers on a later call. poor_fit needs an explicit yes in one of those fields; good_fit needs an explicit no in all three. Having a development team is not the same as wanting Ashley to supply one.

输入参数situation必填wants_a_delivery_teammust_start_within_a_weekwants_spec_built_without_challenge

get_services

Services, pricing, and what he builds on

The three ways an engagement runs (Build, Partner, Consult), the fixed-price diagnostic most engagements start with, how the process works, and which client surfaces he builds: desktop applications, browser extensions, chat-platform integrations and web. Use this for any question about platforms, apps, pricing or how an engagement is structured.

无需输入参数。

list_work

List case studies

Summaries of the selected work, with the slug needed for get_case_study.

无需输入参数。

get_case_study

Read one case study in full

Full detail for one engagement: the situation, what was built, the engineering decisions and why they were made, the stack, and where there is one, the commercial outcome in indexed figures.

输入参数slug必填

get_ai_capability

How he approaches AI work

Which AI techniques he has built in production (prompting, retrieval, fine-tuning, MCP servers, local inference) and when each one is the right choice. Use this for questions about AI, automation or data privacy.

无需输入参数。

search_insights

Search his writing

Search his articles on technical leadership, fractional CTO work, AI and building SaaS. Returns titles, summaries and the matching passage. Call get_insight with a slug for the full text of one.

输入参数query

get_insight

Read one article in full

The complete text of one article, by slug. Use after search_insights, and only when the summary is not enough to answer the question.

输入参数slug必填

get_faqs

Common questions

The questions buyers ask, with his answers. Pass a query to get the relevant ones; omit it to list every question without the answers.

输入参数query

get_contact

How to get in touch

How to reach Ashley: email, the contact page, and a booking link when one is live. Use when the person wants to make contact.

无需输入参数。

get_evidence

How the numbers are counted

Where the numbers on the site come from, for when someone asks whether they can be trusted. Returns one statement of provenance: the figures are counts from live systems, self-reported with a stated method and not independently audited, and Ashley will run any of them in front of someone who asks. Per-figure detail (the collections, queries and returned values) is not published.

无需输入参数。

get_privacy

What happens to your data

What this connector and the website do with data, and what they do not. Use this if the person asks about privacy, tracking, cookies, GDPR, or what Ashley can see of this conversation.

无需输入参数。

版本历史

2
  1. v1.0.1最新Oct 15, 2026
  2. v1.0.0Oct 13, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。