MCP100 verdict
Not currently recommended. First-party or well-evidenced implementation identity, meaningful task value, maintained setup evidence, and no material admission veto were found in reviewed sources.
MCP100 Assessment
Editorial verdict
Reviewed October 19, 2026
Task Fit
Mapped
Developer workflows
Trust
Status warning
Shortlist evidence is sufficient for identity, setup and task value; authenticated runtime tool-schema measurement and exhaustive security certification remain out of scope.
Maintenance
Date unavailable
No dated repository or package update is currently stored.
Popularity
Signals available
Visible usage signals are shown for discovery only, not as proof of safety.
Evidence scope
37 MCP repository stars
37.4k package downloads / 30 days
Repository identity: SAP/mdk-mcp-server
Package identity: @sap/mdk-mcp-server · version 0.4.0
Stars observed October 20, 2026 · Downloads observed October 20, 2026
Current first-party SAP MDK MCP implementation repository.
Exact published MCP package. The repository main branch already contains version 0.5.0 metadata, but the reviewed npm registry latest is 0.4.0; published version is used for package evidence.
Publisher activity observed October 20, 2026
Current source snapshot
Source relationship: First-party MCP
Reviewed October 19, 2026
Evidence-backed setup
Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.
Transport not recorded
Complete client-specific setup, verification and removal are not documented in this reviewed source.
Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.
Evidence checked 2026-10-20
Type-appropriate, source-backed setup for this mcp server profile.
Loading optional publisher installation details…
{"command":"npx","args":["-y","@sap/mdk-mcp-server"],"optionalEnv":{"SAP_UX_FIORI_TOOLS_DISABLE_TELEMETRY":"true"}}Capability
SAP’s official MDK MCP server provides project generation, lifecycle management, documentation and SAP Mobile Services metadata tools. Several tools write files, build/deploy projects, or access SAP Mobile Services. The metadata-fetch tool requires Cloud Foundry authentication. Telemetry is enabled by default but can be disabled with SAP_UX_FIORI_TOOLS_DISABLE_TELEMETRY=true.
Not measured yet
Estimated token footprint of the MCP tool schemas exposed to the agent.
@sap/mdk-mcp-server
Reviewed access
Reviewed sources
Related reviewed MCPs
Retrieve current library and framework documentation for coding agents.
Choose this instead if
Choose Context7 MCP instead if current library and API documentation inside coding agents.
Retrieve current library and framework documentation for coding agents.
Discover and run MCP servers through Docker's MCP gateway.
Choose this instead if
Choose Docker MCP Gateway instead if running multiple MCP servers behind one stdio connection.
Discover and run MCP servers through Docker's MCP gateway.
Work with repositories, issues, pull requests, and GitHub workflows.
Choose this instead if
Choose GitHub MCP instead if repository, issue, pull-request, and code context.
Work with repositories, issues, pull requests, and GitHub workflows.
SAP is listed as First-party MCP in MCP100’s current evidence.
Current official resources:
From the publisher README
Original client setup and configuration retained from the publisher documentation.
Publisher-documented clients
These names appear in the publisher's installation documentation. MCP100-verified configurations are shown separately above when available.
The MDK MCP server supports the following platforms:
If you're on an Intel Mac, you may need to:
Install node.js 24.11.1.
To install the MDK MCP server, you have two options:
a. Use npm to install it from the public npmjs registry at @sap/mdk-mcp-server.
npm install -g @sap/mdk-mcp-server
b. Clone the open-source code repository at https://github.com/SAP/mdk-mcp-server, and use npm to install.
git clone https://github.com/SAP/mdk-mcp-server.git
cd mdk-mcp-server
npm i
npm run build
npm i -g @sap/mdk-mcp-server@.
Configure your MCP client (AI agent) to connect to the server. Note that configuration will vary depending on the AI agent used.
Cline in VS Code: Example using the Cline extension.
cline_mcp_settings.json file in your editor.mcpServers section, and save the file. The supported schema versions include 26.9 (default), 26.6, 26.3, 25.9, 25.6, 24.11, and 24.7.{
"mcpServers": {
"mdk-mcp": {
"type": "stdio",
"command": "mdk-mcp",
"args": ["--schema-version", "26.9"]
}
}
}
Note:
If the MCP server is not listed with its available tools in the Cline extension immediately, restart VS Code.
Claude Code discovers MCP servers from its configuration.
~/.claude.json
{
"mcpServers": {
"mdk-mcp": {
"type": "stdio",
"command": "mdk-mcp",
"args": ["--schema-version", "26.9"]
}
}
}
Note: If
~/.claude.jsonalready exists, merge themdk-mcpentry into the existingmcpServerssection rather than replacing the entire file.
Open the Claude Code panel in VS Code and run:
/mcp
You should see mdk-mcp listed as an available MCP server.
An example using OpenCode:
{
"mcp": {
"mdk-mcp": {
"type": "local",
"command": ["mdk-mcp", "--schema-version", "26.9"],
"enabled": true
}
}
}
Edit the file ~/.cursor/mcp.json:
{
"mcpServers": {
"mdk-mcp": {
"type": "stdio",
"command": "mdk-mcp",
"args": ["--schema-version", "26.9"]
}
}
}
Find your Node.js installation path by running the terminal command:
which node
This might output something like /usr/local/bin/node or /opt/homebrew/bin/node.
Edit ~/Library/Application Support/Claude/claude_desktop_config.json and update the command field to use the absolute path:
{
"mcpServers": {
"mdk-mcp": {
"command": "/usr/local/bin/node",
"args": ["/usr/local/lib/node_modules/@sap/mdk-mcp-server/build/index.js", "--schema-version", "26.9"]
}
}
}
Restart Claude Desktop.
Note: Adjust the paths based on your actual Node.js and MDK MCP server installation locations.
Once configured, your AI agent will have access to the MDK MCP server. Depending on your IDE settings, you may need to approve initial tool calls.
Create a Rule File: To ensure your AI coding assistant uses the MCP servers appropriately for your project, define rules and guidelines in a file named AGENTS.md. In the Cline extension for VS Code, click the Manage Cline Rules & Workflows icon below the prompt box, click + to create a new rule file (e.g., AGENTS.md) and add the example rules shown below:
- Do not generate `.service.metadata` file.
- Do not generate `.xml` file in the `Services` folder.
- Do not change `.project.json` file.
Verify your LLM Provider and AI model.
When you add Cline to VS Code, it serves as the default API provider. You can choose a different LLM provider, such as SAP AI Core. To add an SAP AI Core API provider in the Cline extension for VS Code, follow these steps:
Integration with SAP Mobile Services: To create a new MDK application, the MCP server uses the Cloud Foundry CLI and a .service.metadata file containing:
We include a tool to help with creating or updating this file as part of our VS Code extension: Mobile development kit extension for VS Code. This is how you can use this tool to create or update the .service.metadata file:
cf login -a <your target endpoint> --sso
Your environment is now ready for the MDK development with MCP server. You can now enter a prompt to:
Extract the ilodata tool:
# Download MDK SDK and locate the tools zip file
unzip SAPOfflineOData-*.zip -d ~/ilodata-tools
Prepare your offline store files:
# Copy your offline store files to the ilodata folder
cp /path/to/your/app/*.udb ~/ilodata-tools/
cp /path/to/your/app/*.rq.udb ~/ilodata-tools/
Original product, capability, tool, and usage documentation from the MCP publisher. Installation sections appear under Install & Agents.
This open-source server provides AI agents with comprehensive MDK knowledge and tools. By combining best practice guidelines, project-aware context information, templates for creating new projects, and access to the MDK CLI tools, the MDK MCP server transforms AI agents into MDK development experts.
The mobile development kit is a powerful framework that enables developers to build cross-platform mobile applications using a metadata-driven approach. It is part of SAP Business Technology Platform and integrates tightly with SAP Mobile Services. Some of SAP’s larger and complex mobile apps are built using MDK. An example is SAP Service and Asset Manager.
[!NOTE] Tools are meant to be used by AI models and do not constitute a stable API.
This release of the MDK MCP server includes the following tools, which can be accessed by your AI agent:
| Tools | Description | Parameters |
|---|---|---|
mdk-create | Creates MDK projects or entity metadata using templates (CRUD, List Detail, Base). Use this for initializing new projects or adding entity metadata to existing projects. | - folderRootPath: The path of the current project root folder. - scope: The scope of creation:• project: Initialize a new MDK project with full structure• entity: Add entity metadata to an existing project - templateType: The type of template to use (crud, list detail, base). Note: base template is only valid for project scope. - oDataEntitySets: The OData entity sets relevant to the user prompt, separated by commas. - offline: Whether to generate the project in offline mode (only applicable for project scope). Set to false unless offline is explicitly specified. |
mdk-gen | Generates MDK artifacts including pages, actions, i18n files, and rule references. Returns prompts for LLM processing (pages, actions, i18n) or searches for rule examples. | - artifactType: The type of artifact to generate:• page: Generate MDK page files (.page) with databinding or layout• action: Generate MDK action files (.action)• i18n: Generate internationalization files (.properties)• rule: Search for and return relevant JavaScript rule examples - folderRootPath: The path of the current project root folder (not required for rule artifact type).For page artifacts: - pageType: Type of page page):• databinding: Data-driven pages with controls bound to OData• layout: Structure-focused pages with specific layouts - controlType: The control type for databinding pages (required when pageType is databinding). Available types: ObjectTable, FormCell, KeyValue, ObjectHeader, ContactTable, SimplePropertyCollection, ObjectCard, DataTable, KPIHeader, ProfileHeader, ObjectCollection, Timeline, TimelinePreview, Calendar. - oDataEntitySets: Optional: The OData entity sets to use for page generation, separated by commas (required only when pageType is databinding). - layoutType: The layout type for layout pages (required when pageType is layout). Available types: Section, BottomNavigation, FlexibleColumnLayout, SideDrawerNavigation, Tabs, Extension.For action artifacts: - actionType: The type of action (required when artifactType is action). Available types: CreateODataEntity, UpdateODataEntity, DeleteODataEntity, CreateODataMedia, InitializeOfflineOData, DownloadOfflineOData, UploadOfflineOData, CancelDownloadOfflineOData, CancelUploadOfflineOData, ClearOfflineOData, CloseOfflineOData, CreateODataRelatedEntity, CreateODataRelatedMedia, CreateODataService, DeleteODataMedia, DownloadMediaOData, LogMessage, Message, Navigation, OpenODataService, ProgressBanner, PushNotificationRegister, PushNotificationUnregister, ReadODataService, RemoveDefiningRequest, SendRequest, SetLevel, SetState, ToastMessage, UndoPendingChanges, UploadLog, UploadODataMedia, UploadStreamOData, ChatCompletion, PopoverMenu, CheckRequiredFields, ChangeSet, OpenDocument, Banner, Filter. - oDataEntitySets: Optional: The OData entity sets to use for action generation, separated by commas (required only when artifactType is action).For i18n artifacts: - No additional parameters required beyond folderRootPath.For rule artifacts: - query: Search query for rule reference (required when artifactType is rule). Examples: get app name, handle form validation, navigate to page, etc. |
mdk-manage | Comprehensive MDK project management tool that handles build, deploy, validate, migrate, show QR code, and mobile app editor operations. | - folderRootPath: The path of the current project root folder. - operation: The operation to perform on the MDK project. Available operations:• build: Build an MDK project• deploy: Deploy an MDK project to the Mobile Services• validate: Validate an MDK project• migrate: Migrate an MDK project to the latest MDK version• show-qrcode: Show QR code for an MDK project• open-mobile-app-editor: Instruct how to open the Mobile App Editor to create .service.metadata file - externals: Optional: Array of external package names to include in the deployment (e.g., [@nativescript/geolocation]). If not specified, will automatically read from mdk.bundlerExternals in .vscode/settings.json of the project. Defaults to empty array if neither is provided. |
mdk-docs | Unified tool for accessing MDK documentation including search, component schemas, property details, and examples. | - operation: The type of documentation operation to perform:• search: Returns the top N results from MDK documentation by semantic search, sorted by relevance• component: Returns the schema of an MDK component based on the name of the component• property: Returns the documentation of a specific property of an MDK component• example: Returns an example usage of an MDK component• search-samples: Search through MDK tutorial samples and code examples from GitHub - folderRootPath: The path of the current project root folder. Used to determine the appropriate MDK schema version. - query: Search query string (required for search and search-samples operations). - component_name: Name of the component (required for component, property, and example operations). - property_name: Name of the property (required for property operation). - N: Number of results to return for search operation (default: 5). |
mdk-fetch-mobile-metadata | Fetches OData $metadata document from a Mobile Services destination and saves it as a .service.metadata file in the MDK project. This file is required by mdk-create and mdk-gen tools for data-bound page/action generation. Requires CF CLI authentication (cf login). | - folderRootPath: The path of the MDK project root folder where .service.metadata will be saved. - appId: The Mobile Services application ID (e.g., myapp.mdk.demo). - destination: The destination name configured in Mobile Services (e.g., IncidentManagement). - pathSuffix: Optional path suffix to append before /$metadata (e.g., /api/v1). Leave empty if not needed. - landscapeType: The Mobile Services landscape type. Use Standard for production environments (default) or Preview for preview environments. |
The MDK MCP server can ingest additional knowledge from GitHub repositories to enhance the search-samples operation. This allows the AI agent to search through MDK tutorial samples and code examples.
By default, the server ingests knowledge from:
You typically only need to run ingestion in these scenarios:
search-samples operation)Note: The ingestion process is optional. The server will work without it, but the
search-samplesoperation will not return results until ingestion is completed.
Basic ingestion (uses cached data if available):
npm run ingest
Fresh ingestion (ignores cache, re-downloads everything):
npm run ingest:fresh
With GitHub token (recommended for better rate limits):
export GITHUB_TOKEN="your_github_token_here"
npm run ingest
Custom options:
npm run build
node build/ingest-github-knowledge.js --no-cache --github-token "your_token" --chunk-size 800
| Option | Description | Default |
|---|---|---|
--no-cache | Force re-download of all content, ignoring cache | Uses cache |
--github-token <token> | GitHub personal access token for API requests | $GITHUB_TOKEN env var |
--vector-db <path> | Path to store the vector database | ./knowledge.db |
--chunk-size <number> | Size of text chunks for embedding | 1000 |
--chunk-overlap <number> | Overlap between chunks | 200 |
To avoid GitHub API rate limits, create a personal access token:
public_repo (read access to public repositories)export GITHUB_TOKEN="ghp_your_token_here"
The ingestion process will:
search-samples operationExample output:
Fetching from MDK Tutorial Samples...
Chunking content: 150 chunks created
Generating embeddings: 150/150 (100%)
✓ Ingestion complete!
Issue: GitHub API rate limit exceeded
Issue: Ingestion takes too long
--no-cache only when necessary; cached runs are much fasterIssue: Out of memory
--chunk-size or process fewer repositoriesThe MDK MCP server can help you query offline OData stores using the ilodata command-line tool. This is useful for debugging offline applications or inspecting data stored locally on devices during development.
SAPOfflineOData-xx.xx.xx-Tools.zip in the MDK SDK.udb and .rq.udb files from your offline applicationOnce set up, you can use natural language prompts with the MDK MCP server to query offline stores:
Basic query:
Open and query the CustomerStore offline store located at ~/ilodata-tools/CustomerStore.udb
and retrieve the top 5 entities from the Customers entity set
Filtered query:
Query the SalesOrders offline store at ~/ilodata-tools/SalesOrders.udb
and get all orders where CustomerID equals `ALFKI`
Specific fields:
Open the Products offline store at ~/ilodata-tools/Products.udb
and retrieve ProductID, ProductName, and UnitPrice from the Products entity set
Count entities:
Query the Employees offline store at ~/ilodata-tools/Employees.udb
and count the total number of records in the Employees entity set
The AI agent will:
ilodata commandThis project is open to feature requests/suggestions, bug reports, and so on, via GitHub issues. Contribution and feedback are encouraged and always welcome.
These instructions help contributors set up, test, and maintain code quality for this project. All commands should be run from your project folder in a terminal.
npm testnpm run buildnpm run lint:allFor more information about how to contribute, the project structure, as well as additional contribution information, see our Contribution Guidelines.
You can enable or disable the collection of analytics. By default, non-personally identifiable information is collected to help understand how you use the product and improve the MDK MCP Server. If you want to opt-out, there are two ways to disable 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 disables the telemetry client.
If you find a bug that may pose a security problem, please follow our instructions in our security policy on how to report it. Please do not create GitHub issues for security-related doubts or problems.
As members, contributors, and leaders, we pledge to make participation in our community a harassment-free experience for everyone. By participating in this project, you agree to abide by its Code of Conduct at all times.
Copyright 2025 SAP SE or an SAP affiliate company. Please see our LICENSE for copyright and license information. Detailed information including third-party components and their licensing/copyright information is available .