Ricky Moorhouse's blog

uk.rickymoorhouse由 rickymoorhouse.uk 发布官方发布者v0.2.0更新于 Nov 16, 2026

Search and read Ricky Moorhouse's posts on API architecture, API Connect, SRE, AI and travel.

已验证Streamable HTTP可网页运行位置与生活

概览

Ricky Moorhouse's blog 的托管 MCP 服务(mcp.rickymoorhouse.uk),由 rickymoorhouse.uk 发布;无需登录;Streamable HTTP;3 个工具。

暂无 AI 概览:以下信息来自注册中心条目和服务本身。

发布者
rickymoorhouse.uk
端点
mcp.rickymoorhouse.uk
最近检查

安装

在 SourceWeft 中

  1. 打开 控制台中的 Ricky Moorhouse's blog,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.rickymoorhouse%2Fblog/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": {
    "ricky-moorhouse-s-blog": {
      "type": "http",
      "url": "https://mcp.rickymoorhouse.uk/mcp"
    }
  }
}

README

Blog MCP server

A small, read-only MCP server for rickymoorhouse.uk. It lets AI assistants search and read the blog, microblog, talks and projects.

It only reads the published site, so it can run anywhere with internet access:

  • search.json is built by Hugo (themes/2026/layouts/home.search.json). It holds one entry per post with the title, URL, date, section, tags, description and plain text.
  • The server loads search.json into an in-memory MiniSearch index. It reloads the index in the background every 10 minutes.
  • get_post fetches a page's index.md from the site.

It uses the Streamable HTTP transport in stateless JSON mode. There are no sessions and no auth, and the endpoint is /mcp.

Protocol versions

EraVersionsHow it works
Modern2026-07-28Stateless. Every request carries _meta["io.modelcontextprotocol/protocolVersion"] and _meta["io.modelcontextprotocol/clientCapabilities"], and there's no initialize. Results include resultType: "complete" and _meta["io.modelcontextprotocol/serverInfo"].
Legacy2025-11-25, 2025-06-18, 2025-03-26, 2024-11-05Negotiated once with initialize, as before.

The server works out the era for each request. A request is modern if its _meta carries a protocol version, or if its MCP-Protocol-Version header names a version that isn't legacy. Everything else is legacy, including initialize and requests without the header (the spec says to treat those as 2025-03-26).

Modern requests are checked before they run:

  • If either _meta field is missing, the server returns -32602 with HTTP 400.
  • If the MCP-Protocol-Version header doesn't match the _meta version, it returns -32020 (header mismatch) with HTTP 400. The same goes for the optional Mcp-Method and Mcp-Name headers if they don't match the body.
  • If the version isn't supported, it returns -32022 with HTTP 400 and data.supported listing every version.
  • ping was removed in the modern protocol, so it and any other unknown method get -32601 with HTTP 404.
  • Batches are legacy only. A JSON array that contains a modern message gets -32600 with HTTP 400.

server/discover returns the supported versions, capabilities and instructions, with ttlMs and cacheScope: "public" so clients can cache it. Modern tools/list is cacheable for a day. server/discover also answers legacy callers.

The server ignores any Mcp-Session-Id header and never sets one. GET and DELETE on /mcp return 405.

Tools

ToolArgumentsReturns
search_postsquery, plus optional section (blog, microblog, talks, projects), tag and limit (default 10, max 50)Matching posts with title, URL, Markdown URL, date, section, category, tags, description and score
get_posturl of a page on the siteThe page as Markdown
list_recentoptional section and limitThe newest posts, in the same shape as search results

Discovery

The server publishes an MCP Server Card at <endpoint>/server-card, for example https://blog-mcp-xfh2k.bunny.run/mcp/server-card. Server Cards are experimental (SEP-2127). The card is a static JSON description of the server that clients can read before connecting: name, version, title, description, website, repository, icon, and the Streamable HTTP endpoint with its supported protocol versions.

  • The card is built in main.ts from the same SERVER_INFO and version lists that initialize and server/discover use, so they can't drift. It lists both modern and legacy versions.
  • The endpoint URL comes from the request host, so the card stays correct on a custom domain.
  • Following the spec, it doesn't list tools. Clients get those from tools/list.
  • It's served as application/mcp-server-card+json, with the CORS, Cache-Control and ETag headers the spec asks for, and it answers If-None-Match with a 304.

The blog advertises the server in an AI Catalog at https://rickymoorhouse.uk/.well-known/ai-catalog.json, from static/.well-known/ai-catalog.json. That catalog is where domain-level discovery starts. Its entry points at the Server Card URL above, so update it if the server's hostname changes.

MCP Registry

server.json describes the server for the official MCP Registry. It uses the 2025-12-11 schema and points at https://mcp.rickymoorhouse.uk/mcp. Keep its version in step with SERVER_INFO.version in main.ts, and its description in step with the Server Card. The registry limits the description to 100 characters.

The name uk.rickymoorhouse/blog is in the reverse-DNS form, so the registry checks that you control rickymoorhouse.uk using HTTP domain authentication:

  1. Generate an Ed25519 key pair with openssl genpkey -algorithm Ed25519 -out key.pem, and keep key.pem out of the repository. On macOS this needs OpenSSL 3 (brew install openssl@3), because the system LibreSSL can't make Ed25519 keys.
  2. Publish the public key at https://rickymoorhouse.uk/.well-known/mcp-registry-auth by adding it as static/.well-known/mcp-registry-auth, then deploy the site. The file is one line, v=MCPv1; k=ed25519; p=<base64 public key>. The registry's authentication guide has the command to make it.
  3. Log in and publish from this folder. Passing the key in MCP_PRIVATE_KEY keeps it off the command line:
bash
MCP_PRIVATE_KEY="$(openssl pkey -in key.pem -noout -text | sed -n '/priv:/,/pub:/p' | sed '1d;$d' | tr -d ' :\n')" mcp-publisher login http --domain rickymoorhouse.uk
bash
mcp-publisher publish

Configuration

VariableDefault
SITE_URLhttps://rickymoorhouse.ukWhere to fetch search.json and the Markdown pages from
INDEX_TTL_SECONDS600How long before the index is reloaded
PORT8080Local runs only; Bunny ignores it

Running locally

It needs Deno 2.

bash
cd mcpPORT=8766 deno task dev

To test against a local build instead of the live site, build the site and serve public/:

bash
hugo && python3 -m http.server 8765 -d public
bash
cd mcp && PORT=8766 SITE_URL=http://localhost:8765 deno task dev

Check it with the MCP Inspector:

bash
npx @modelcontextprotocol/inspector --cli http://127.0.0.1:8766/mcp --transport http --method tools/list

Or with plain JSON-RPC:

bash
curl -s http://127.0.0.1:8766/mcp -H 'content-type: application/json' -H 'accept: application/json, text/event-stream' -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search_posts","arguments":{"query":"observability","limit":3}}}'

A modern request carries the version in a header and in _meta:

bash
curl -s http://127.0.0.1:8766/mcp -H 'content-type: application/json' -H 'accept: application/json, text/event-stream' -H 'mcp-protocol-version: 2026-07-28' -d '{"jsonrpc":"2.0","id":1,"method":"server/discover","params":{"_meta":{"io.modelcontextprotocol/protocolVersion":"2026-07-28","io.modelcontextprotocol/clientCapabilities":{}}}}'

Deploying to Bunny Edge Scripting

  1. Make sure the site has been deployed with search.json. Check that https://rickymoorhouse.uk/search.json loads.
  2. In the Bunny dashboard, go to Edge Platform → Scripts → Add script, and choose a Standalone script. Either paste in main.ts, or connect the GitHub repository with mcp/main.ts as the entry file.
  3. You only need to set environment variables if you want something other than the defaults.
  4. Add a custom hostname, such as mcp.rickymoorhouse.uk, to the script's pull zone and point a CNAME at it.
  5. Check it: npx @modelcontextprotocol/inspector --cli https://mcp.rickymoorhouse.uk/mcp --transport http --method tools/list

Adding it to an MCP client

Claude Code:

bash
claude mcp add --transport http rickymoorhouse-blog https://mcp.rickymoorhouse.uk/mcp

Claude desktop and claude.ai: Settings → Connectors → Add custom connector, using the /mcp URL.

Other clients: add it as a remote, Streamable HTTP server with the URL https://mcp.rickymoorhouse.uk/mcp.

来源:mcp/README.md,提交 587ad26

工具

3

search_posts

Search posts

Full-text search across Ricky Moorhouse's blog posts, microblog notes, talks and projects. Covers API architecture, IBM API Connect, SRE, observability and AI agents, plus travel, photography and walking. Returns matching posts with their URL, date, tags and description; use get_post to read one in full.

输入参数taglimitquery必填section

get_post

Get post

Fetch the full text of a page on rickymoorhouse.uk as Markdown, given its URL.

输入参数url必填

list_recent

List recent posts

List the most recent posts, newest first, optionally from one section.

输入参数limitsection

版本历史

1
  1. v0.2.0最新Nov 16, 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。