Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Coding guidelines and best-practice guides for 130+ languages, frameworks, and tools.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://codeguide-mcp-86057491046.europe-west1.run.app/mcp打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"codeguide": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/delian/codeguide-mcp:0.1.0"
]
}
}
}在终端中运行这条命令
claude mcp add --transport http codeguide https://codeguide-mcp-86057491046.europe-west1.run.app/mcpclaude mcp add codeguide -- docker run -i --rm docker.io/delian/codeguide-mcp:0.1.0粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"codeguide": {
"url": "https://codeguide-mcp-86057491046.europe-west1.run.app/mcp"
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"codeguide": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/delian/codeguide-mcp:0.1.0"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"codeguide": {
"type": "http",
"url": "https://codeguide-mcp-86057491046.europe-west1.run.app/mcp"
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"codeguide": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/delian/codeguide-mcp:0.1.0"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://codeguide-mcp-86057491046.europe-west1.run.app/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过 GitHub 账户 delian 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(0.1.0)于3个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Spec Driven Development, Remote Desktop Commander, AI Deprecations
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
AI model shutdown dates, replacements, change feed and webhook alerts for 8 providers.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
A Model Context Protocol (MCP) server that provides access to coding guides and best practices for AI assistants like Claude and GitHub Copilot.
This MCP server exposes coding guidelines and style guides as resources that can be accessed by MCP clients. It's designed to extend or replace AGENTS.md files by providing a structured way to serve coding practices and guidelines to AI assistants during development.
mcp SDK (MCPServer, formerly FastMCP)guides://list - Lists all available coding guidesguides://{guide_name} - Retrieves the content of a specific guide (e.g., guides://python.md)# Clone the repository
git clone https://github.com/delian/codeguide-mcp.git cd codeguide-mcp
uv sync
pip install -e .
docker build -t codeguide-mcp .
docker run -i codeguide-mcp
Or search for codeguide-mcp in the Extensions view MCP servers list (type @mcp in the Extensions search bar), or add it manually to .vscode/mcp.json:
{
"servers": { "codeguide-mcp": { "command": "docker", "args": ["run", "-i", "--rm", "delian/codeguide-mcp"] } } }
Configure the server by creating a config.toml file or setting environment variables:
To load guides from a GitHub repository:
github_repo = "owner/repository" # e.g., "delian/codeguide-mcp"
github_path = "guides" # Path to guides directory in repo github_branch = "main" # Branch to fetch from cache_dir = ".guides-cache" # Local cache directory log_level = "INFO"
To use local guides only:
guides_dir = "guides"
log_level = "INFO"
GUIDES_GITHUB_REPO - GitHub repository (format: owner/repo)GUIDES_GITHUB_PATH - Path to guides directory in repository (default: guides)GUIDES_GITHUB_BRANCH - Branch to fetch from (default: main)GUIDES_CACHE_DIR - Local cache directory (default: .guides-cache)GUIDES_DIR - Local directory containing guide files (default: guides)GUIDES_LOG_LEVEL - Logging level (default: INFO)Transport (see Remote deployment):
GUIDES_TRANSPORT - stdio, streamable-http, or auto (default: auto — HTTP when a PORT env var is present, stdio otherwise)PORT - Port to listen on in HTTP mode; takes precedence over GUIDES_PORT (Cloud Run injects this)GUIDES_HOST - Bind address in HTTP mode (default: 0.0.0.0)GUIDES_HTTP_PATH - MCP endpoint path (default: /mcp)GUIDES_STATELESS_HTTP - Handle each request independently (default: true; required when replicas autoscale)GUIDES_ALLOWED_HOSTS - Host header allowlist enabling DNS-rebinding protection (default: empty = no Host validation)guides_dir if configuredThe same image serves both transports: it speaks stdio over a pipe by default, and switches to Streamable HTTP when a PORT env var is present — which Cloud Run always injects. No separate image or entrypoint is needed.
docker build -t delian/codeguide-mcp:0.1.0 -t delian/codeguide-mcp:latest .
docker push delian/codeguide-mcp:0.1.0 docker push delian/codeguide-mcp:latest
gcloud run deploy codeguide-mcp \
--image=docker.io/delian/codeguide-mcp:0.1.0 \ --region=europe-west1 \ --allow-unauthenticated \ --port=8080 \ --set-env-vars=GUIDES_TRANSPORT=streamable-http,GUIDES_GITHUB_REPO= \ --memory=512Mi --cpu=1 \ --min-instances=0 --max-instances=4 --concurrency=40
GUIDES_GITHUB_REPO= (empty) makes the service serve the guides baked into the image. Leaving GitHub enabled adds a network round-trip per guide and runs into the unauthenticated GitHub API limit of 60 requests/hour per egress IP, after which the server silently falls back to those same baked-in files anyway.
The MCP endpoint is then https:// /mcp:
gcloud run services describe codeguide-mcp --region=europe-west1 \
--format='value(status.url)'
Cloud Run answers on two hostnames for the same service — the SERVICE-PROJECTNUMBER.REGION.run.app form printed by gcloud run deploy, and the older SERVICE-HASH-REGIONCODE.a.run.app form that status.url reports. Both are equivalent; either works in a client config.
See Connecting to a remote server below for the per-client configuration.
Cloud Run deploys public Docker Hub images directly, but caches them for only an hour and re-pulls anonymously afterwards, so a scale-up can hit Docker Hub's anonymous pull limits and fail to start instances. For anything beyond casual use, mirror through an Artifact Registry remote repository:
gcloud artifacts repositories create dockerhub \
--repository-format=docker --location=europe-west1 \ --mode=remote-repository --remote-docker-repo=DOCKER-HUB
gcloud run deploy codeguide-mcp \ --image=europe-west1-docker.pkg.dev/PROJECT_ID/dockerhub/delian/codeguide-mcp:0.1.0 \ ...
--allow-unauthenticated makes the endpoint world-callable. The server is read-only, but the clear_cache prompt is reachable by any caller and drops the in-memory caches, and traffic drives autoscaling cost — keep --max-instances capped. To restrict access, omit the flag and have clients send an identity token, or front the service with Cloud Armor / API Gateway.GUIDES_STATELESS_HTTP must stay true unless you also enable session affinity, since Cloud Run may route a session's requests to different instances.GET / returns 404 by design; only /mcp is served. Cloud Run's default startup probe is a TCP check on $PORT, so this is fine — don't configure an HTTP health check on /.GUIDES_ALLOWED_HOSTS to your service hostname to enable Host-header validation if you expose the service under a custom domain.The MCP servers list in the VS Code Extensions view (type @mcp in the search bar) is fed by the GitHub MCP Registry, which ingests from the official MCP Registry. Publishing there is therefore how this server becomes discoverable in VS Code — no VS Code extension of its own is required.
server.json holds the registry metadata: the Docker image for clients that want to run it locally, and the hosted URL for clients that would rather not. Ownership of the image is proven by the io.modelcontextprotocol.server.name label in the Dockerfile, whose value must equal .name in server.json.
Authenticate once (an interactive device-code flow), then run the publish script:
mcp-publisher login github # namespace io.github.<your-username>/*
tools/publish.sh
tools/publish.sh does the whole release: it checks the required tooling and Docker login, verifies that server.json and pyproject.toml agree on the version and that the Dockerfile label matches the server name, builds and pushes :VERSION and :latest, validates server.json against the live registry, publishes, then reads the entry back to confirm.
tools/publish.sh --dry-run # everything except push and publish
tools/publish.sh --version 0.2.0 # bump server.json + pyproject + image tag, then release tools/publish.sh --skip-build # reuse images already on Docker Hub
Install mcp-publisher from the registry quickstart if you do not have it. After publishing, inclusion in GitHub's curated list may need a request to partnerships@github.com.
If you've configured github_repo, simply add Markdown files to the specified directory in your GitHub repository. The server will automatically fetch and cache them.
Add Markdown files to the guides/ directory. Each file will be automatically available as a resource.
Example:
echo "# Python Style Guide\n\nUse PEP 8..." > guides/python.md
The server can be consumed two ways:
| Mode | Transport | How the client reaches it |
|---|---|---|
| Local | stdio | Client spawns python main.py or docker run -i and talks over a pipe |
| Remote | Streamable HTTP | Client makes HTTPS requests to a hosted …/mcp URL |
Local mode needs no network and no hosting; remote mode lets a team share one deployment and keeps the guides identical for everyone.
A deployed instance exposes its MCP endpoint at /mcp. The snippets below use the reference deployment:
https://codeguide-mcp-86057491046.europe-west1.run.app/mcp
It is public and needs no credentials. Substitute your own URL if you run the service yourself — see Remote deployment.
VS Code — .vscode/mcp.json for one workspace, or your user mcp.json for every workspace:
{
"servers": { "codeguide-mcp": { "type": "http", "url": "https://codeguide-mcp-86057491046.europe-west1.run.app/mcp" } } }
Claude Code:
claude mcp add --transport http codeguide-mcp \
https://codeguide-mcp-86057491046.europe-west1.run.app/mcp
Cursor — ~/.cursor/mcp.json (global) or .cursor/mcp.json (per project):
{
"mcpServers": { "codeguide-mcp": { "url": "https://codeguide-mcp-86057491046.europe-west1.run.app/mcp" } } }
Claude Desktop — add it as a custom connector in Settings, or bridge the remote endpoint into a stdio client with mcp-remote:
{
"mcpServers": { "codeguide-mcp": { "command": "npx", "args": ["-y", "mcp-remote", "https://codeguide-mcp-86057491046.europe-west1.run.app/mcp"] } } }
Any client that speaks Streamable HTTP works — point it at the /mcp URL. For servers behind authentication, pass a token with --header "Authorization: Bearer $(gcloud auth print-identity-token)" (Claude Code) or the client's equivalent headers block.
A single curl confirms a deployment is live and public:
curl -s -X POST https://codeguide-mcp-86057491046.europe-west1.run.app/mcp \
-H 'Content-Type: application/json' \ -H 'Accept: application/json, text/event-stream' \ -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{ "protocolVersion":"2025-06-18","capabilities":{}, "clien
只显示了开头部分;其余内容请在仓库中阅读