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)
SAP Fiori - Model Context Protocol (MCP) server
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。
LOG_LEVEL, SAP_UX_FIORI_TOOLS_DISABLE_TELEMETRY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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"fiori": {
"command": "npx",
"args": [
"-y",
"@sap-ux/fiori-mcp-server"
],
"env": {
"LOG_LEVEL": "your-value",
"SAP_UX_FIORI_TOOLS_DISABLE_TELEMETRY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add fiori --env LOG_LEVEL=your-value --env SAP_UX_FIORI_TOOLS_DISABLE_TELEMETRY=your-value -- npx -y @sap-ux/fiori-mcp-server运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"fiori": {
"command": "npx",
"args": [
"-y",
"@sap-ux/fiori-mcp-server"
],
"env": {
"LOG_LEVEL": "your-value",
"SAP_UX_FIORI_TOOLS_DISABLE_TELEMETRY": "your-value"
}
}
}
}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": {
"fiori": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@sap-ux/fiori-mcp-server"
],
"env": {
"LOG_LEVEL": "your-value",
"SAP_UX_FIORI_TOOLS_DISABLE_TELEMETRY": "your-value"
}
}
}
}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。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
LOG_LEVEL envSAP_UX_FIORI_TOOLS_DISABLE_TELEMETRY env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。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
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9日
注册名称已通过 GitHub 账户 SAP 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
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
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。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(1.15.20)于9天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Joe Hill, AI partner in Tennessee
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ 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.
Check open times and book a free 15-minute fit call with Joe Hill, or ask Harvey about his work.
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。
@sap-ux/fiori-mcp-serverThis package includes a Model Context Protocol (MCP) server for integration with AI coding assistants.
The server helps AI models create or modify SAP Fiori applications based on prompts, such as:
https://hostname:port/sap/opu/odata4/sap/my_v4_service?sap-client=000_.ℹ️This prompt requires a saved SAP system connection by using the Connection Manager for SAP Systems extension.
For the best experience we recommend using this server alongside @cap-js/mcp-server and @ui5/mcp-server.
The server uses stdio transport and is launched via npx — no global installation required. Pick the section for your MCP client below.
Note: Replace
with the specific version you want to pin to (e.g.1.12.2). The current release version is shown on the npm page. Using a pinned version rather than@latestensures reproducible behaviour and prevents untested updates from being picked up automatically.
Option A — CLI (recommended):
claude mcp add fiori-mcp -- npx --yes @sap-ux/fiori-mcp-server@<version> fiori-mcp
Option B — drop a `.mcp.json` file in your project root:
{
"mcpServers": { "fiori-mcp": { "type": "stdio", "timeout": 600, "command": "npx", "args": ["--yes", "@sap-ux/fiori-mcp-server@ ", "fiori-mcp"] } } }
Open the Cline extension settings and add the server under MCP Servers:
{
"mcpServers": { "fiori-mcp": { "type": "stdio", "timeout": 600, "command": "npx", "args": ["--yes", "@sap-ux/fiori-mcp-server@ ", "fiori-mcp"] } } }
Edit (or create) the MCP config file for your scope:
~/.cursor/mcp.json.cursor/mcp.json in your project root{
"mcpServers": { "fiori-mcp": { "type": "stdio", "timeout": 600, "command": "npx", "args": ["--yes", "@sap-ux/fiori-mcp-server@ ", "fiori-mcp"] } } }
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": { "fiori-mcp": { "type": "stdio", "timeout": 600, "command": "npx", "args": ["--yes", "@sap-ux/fiori-mcp-server@ ", "fiori-mcp"] } } }
For any other MCP client, use the following npx-based configuration:
{
"mcpServers": { "fiori-mcp": { "type": "stdio", "timeout": 600, "command": "npx", "args": ["--yes", "@sap-ux/fiori-mcp-server@ ", "fiori-mcp"] } } }
If you prefer not to use npx, install the package globally first:
npm install -g @sap-ux/fiori-mcp-server
Then use fiori-mcp as the command (no args needed):
{
"mcpServers": { "fiori-mcp": { "type": "stdio", "timeout": 600, "command": "fiori-mcp" } } }
The following rules help guide the AI model to use the server correctly. Add them to your system prompt or rules file:
AGENTS.md or CLAUDE.md in your project root.cursorrules in your project root.windsurfrules## Rules for creation or modification of SAP Fiori elements apps
550e8400-e29b-41d4-a716-446655440001).npm run watch-* script for the app in the package.json.
search_docsSearches SAP Fiori elements, Annotations, UI5, OPA5 Guides, SAP Fiori tools documentation for the given query.
Note: the results are based on the most recent indexed version of UI5 documentation
First-use download:
search_docsuses a local text-embedding model (all-MiniLM-L6-v2, ~86 MB) for semantic search. The model is downloaded from HuggingFace Hub on first use and cached locally (location follows theHF_HOME/TRANSFORMERS_CACHEenvironment variables, defaulting to~/.cache/huggingface/hub). Subsequent starts load the model from the cache with no network access required.
list_fiori_appsScans a specified directory to find existing SAP Fiori applications that can be modified.
list_sap_systemsLists all SAP systems stored in the user's environment (e.g. SAP Fiori tools system store). Use this when the user references a SAP system by name before calling download_odata_service_metadata or generating a Fiori application.
download_odata_service_metadataDownloads the EDMX metadata of a specific OData service from a SAP system and saves it as metadata.xml. Use this before calling generate_fiori_app_odata when the user provides a SAP system reference or service URL.
generate_fiori_app_odataGenerates a new SAP Fiori UI application for OData (non-CAP) projects, for example ABAP RESTful Application Programming Model-based OData services.
generate_fiori_app_capGenerates a new SAP Fiori UI application within an existing SAP Cloud Application Programming Model (CAP) project.
list_functionality (Step 1 of 3)Gets the list of supported modification functionalities for an existing SAP Fiori application. Requires a valid absolute path to the application.
The supported modifications are:
manifest.json properties depending on the app, for example, adding a layout based on the flexibility of the programming model or enabling initial loadget_functionality_details (Step 2 of 3)Gets the required parameters and detailed information for a specific functionality to modify an existing SAP Fiori application.
execute_functionality (Step 3 of 3)Executes a specific functionality to modify an existing SAP Fiori application with provided parameters.
By default, logging is enabled at the error level. To adjust the log level or disable logging completely, you can use the env property in your configuration.
{
"mcpServers": { "fiori-mcp": { "type": "stdio", "timeout": 600, "command": "npx", "args": ["--yes","@sap-ux/fiori-mcp-server@ ", "fiori-mcp"], "env": { "LOG_LEVEL": "debug" } } } }
The following log levels are supported: `off`, `error`, `warn`, `info`, `debug`, and `verbose`.
The logs are stored in the file system at ~/.fioritools/fiori-mcp-server.log
If you need the MCP server to connect to an OData server using a self-signed SSL certificate, you can use one of the following methods.
This is useful when encountering errors such as: unable to get local issuer certificate
Set the NODE_EXTRA_CA_CERTS environment variable to the path of your CA certificate file. Node.js supports multiple file extensions (.pem, .crt, .cer, .cert).
Example Configuration:
{
"mcpServers": { "fiori-mcp": { "type": "stdio", "timeout": 600, "command": "npx", "args": ["--yes", "@sap-ux/fiori-mcp-server@ ", "fiori-mcp"], "env": { "NODE_EXTRA_CA_CERTS": "/path/to/your/certificate.crt" } } } }
Windows Example:
"env": {
"NODE_EXTRA_CA_CERTS": "C:\\temp\\certs\\CustomCA.crt" }
macOS/Linux Example:
"env": {
"NODE_EXTRA_CA_CERTS": "/Users/username/certs/Custom_CA.crt" }
⚠️ Security Warning: Setting
NODE_TLS_REJECT_UNAUTHORIZED=0disables all SSL certificate validation and poses a significant security risk. Only use this in non-production environments.
{
"mcpServers": { "fiori-mcp": { "type": "stdio", "timeout": 600, "command": "npx", "args": ["--yes", "@sap-ux/fiori-mcp-server@ ", "fiori-mcp"], "env": { "NODE_TLS_REJECT_UNAUTHORIZED": "0" } } } }
You can enable and disable the collection of analytics. By default, non-personally identifiable information is used to help understand how you use the product to improve the Fiori MCP Server. In case you want to opt-out there exist two ways to disable the telemetry.
Create or change the file ~/.fioritools/telemetrysettings.json:
{
"telemetrysettings": { "telemetrySetting": { "enableTelemetry": false } } }
Set enableTelemetry to false to disable telemetry collection.
Set the environment variable SAP_UX_FIORI_TOOLS_DISABLE_TELEMETRY to true:
export SAP_UX_FIORI_TOOLS_DISABLE_TELEMETRY=true
Setting this environment variable will disable the telemetry client.
Everyone participating in this joint project is welc
只显示了开头部分;其余内容请在仓库中阅读