Design System Server
An MCP server for accessing and managing design system documentation from a GitHub repository.
Design System MCP Server
This is a Model Context Protocol (MCP) server that provides access to Appian's design system documentation through GitHub repositories. It supports both public and internal documentation sources, allowing LLMs like Claude to query and explore design system components, layouts, and patterns with appropriate access controls.
🔗 Related Resources
- Aurora Design System Documentation: appian-design/aurora - The source repository for design system documentation
- Live Documentation Site: https://appian-design.github.io/aurora/ - Browse the design system online
⚡ Quickstart
For technical users who want to get up and running quickly:
-
Clone and setup:
git clone https://github.com/appian-design/aurora-mcp.git cd aurora-mcp npm install -
Configure GitHub access:
cp .env.example .env # Edit .env with your GitHub token and repository details -
Build and configure MCP:
npm run build # Add to ~/.aws/amazonq/mcp.json or Claude Desktop config -
Test the connection:
npm test
For detailed setup instructions, see the Installation section below.
Features
- Multi-source support: Access both public and internal documentation repositories
- Source attribution: Clear indication of content source (public/internal)
- Priority-based merging: Internal documentation overrides public when both exist
- Access control: Configurable access to internal documentation
- Browse design system categories (components, layouts, patterns, branding, etc.)
- List components within a category with source information
- Get detailed component information including guidance and code examples
- Search across all components by keyword with source filtering
- Source management: View source status and manually refresh content
Installation
Public Documentation Only
For access to public design system documentation only:
- Clone this repository (or fork it to your own GitHub account)
- Copy the environment file and configure it:
cp .env.example .env - Edit
.envand update the values:GITHUB_TOKEN: Your GitHub personal access token (generate at https://github.com/settings/tokens)GITHUB_OWNER: Your GitHub username (the repository owner)GITHUB_REPO: Your repository name (e.g., "aurora")
- Install dependencies:
npm install - Build the server:
npm run build
Internal Documentation Access
For access to both public and internal documentation:
- Follow the public documentation setup above
- Configure internal documentation access in your
.envfile:# Enable internal documentation ENABLE_INTERNAL_DOCS=true # GitHub token for internal repository (must have access to private repo) INTERNAL_DOCS_TOKEN=your_github_token_for_private_repo # Optional: Internal repository owner (defaults to GITHUB_OWNER) INTERNAL_GITHUB_OWNER=your_internal_repo_owner # Optional: Internal repository name (defaults to design-system-docs-internal) INTERNAL_GITHUB_REPO=your_internal_repo_name - Ensure your internal repository follows the same structure as the public one:
- Place documentation files in a
/docsfolder - Use the same category structure (components, layouts, patterns, etc.)
- Place documentation files in a
Advanced Configuration
For detailed configuration options, see Configuration Guide.
Usage with Amazon Q (Appian-specific)
This section will help you set up the Design System MCP Server to work with Amazon Q chat. This tool allows you to query design system components, patterns, and layouts directly through conversational AI, with support for both public and internal documentation sources.
What You'll Need
- Access to our AWS account
- VS Code (recommended)
- Node.js installed on your machine
More on Node.js
Check if it's installed by opening the Terminal app and running this command to see the version: node -v.
If you get a "command not found" message, go to the Node.js download page to get it. You can use the selection tool to run the installation from the command line or the download the binary and run it from your machine.
Pick the current LTS (long-term support) version of Node.
The command line tool will have you pick a node version manager and node package manager. Unless you have a preference for something else, use nvm and npm.
Step 1: Install Amazon Q Chat
[!IMPORTANT] During installation, sign in with the
Use with Pro licenseoption. You will need to locate the start URL from our internal documentation.
- Visit the Amazon Q chat installation page: Amazon Q Developer (Command Line)
- We want to use the command line version (CLI) because it's more reliable and has access to the MCP tools.
- Click "Get Started" and follow the installation instructions for your operating system
- Once installed, you can access Amazon Q through the terminal command line by typing
q chat- Once you start Q, we recommend switching the model to Claude 4 by typing
/modeland choosing that option.
- Once you start Q, we recommend switching the model to Claude 4 by typing
Step 2: Download This Project
You have two options to get the project files:
Option A: Download ZIP (Easier)
- Go to the project's GitHub page
- Click the green "Code" button
- Select "Download ZIP"
- Extract the ZIP file to your Desktop or preferred location
- It will download and extract as
aurora-mcp-main. You can remove the-mainor leave as is but the rest of the instructions assume it's not there.
- It will download and extract as
Option B: Clone with Git (If you're comfortable with Git)
- Open Terminal (Mac) or Command Prompt (Windows)
- Navigate to where you want the project, e.g.,
~/repo/ - Run:
git clone [repository-url]
Step 3: Install the Project
- Open Terminal (Mac) or Command Prompt (Windows)
- Navigate to the project folder, for example:
cd Desktop/aurora - Install the required dependencies:
npm install - Build the project:
npm run build
Step 4: Set Up GitHub Access
The MCP server needs API access to GitHub to fetch the design system documentation. You can set up access for public documentation only, or for both public and internal documentation.
Public Documentation Only (Default Setup)
At a high level, here's what you need to do:
- Create a Personal Access Token (PAT) to allow API access to all public repositories (easier)
- Alternatively, you can fork your own copy of the repo and create a PAT for that one (more for development)
- Copy the PAT to a
.envfile in the folder of your local copy of theaurora-mcprepo
Internal Documentation Access (Optional)
If you need access to internal documentation, you'll also need:
- Access to the internal documentation repository
- A separate GitHub token for the private repository
- Additional environment configuration
Detailed Steps
-
Create a GitHub Personal Access Token:
- Go to GitHub Settings > Developer settings > Personal access tokens > Fine-grained tokens
- Click "Generate new token"
- Give it a descriptive name like "Appian Aurora Docs Access"
- Set expiration to your preference
- Under Repository Access, confirm it's set to
Public repositories - Click "Generate token"
- Important: Copy the token immediately - you won't be able to see it again! (You may want to paste it in a temporary location until setup is complete.)
-
Create a .env file:
-
In the aurora-mcp folder on your machine, run this command in Terminal to copy the example environment file:
cp .env.example .env -
Open the
.envfile in a text editoropen -e .env -
For public documentation only, update these values:
GITHUB_TOKEN: Replace with your actual token from previous stepGITHUB_OWNER: Should be set toappian-design(unless you created a fork)GITHUB_REPO: Should be set toaurora(unless you renamed your fork)
-
For internal documentation access, also add:
ENABLE_INTERNAL_DOCS=trueINTERNAL_DOCS_TOKEN=your_internal_docs_token_here
-
Save and close the file
-
-
Rebuild the project:
npm run build
Step 5: Configure Amazon Q
Now you need to tell Amazon Q where to find this design system server.
-
Set up configuration file:
- Run this command in Terminal to create the empty file in the right place and open it with TextEdit:
mkdir -p ~/.aws/amazonq && touch ~/.aws/amazonq/mcp.json && open -e ~/.aws/amazonq/mcp.json
- Run this command in Terminal to create the empty file in the right place and open it with TextEdit:
-
Get the full path to your project:
- In Terminal/Command Prompt, while in the
aurora-mcpproject folder, run:pwd - Copy the full path that appears and paste it somewhere handy for now (it will look something like
/Users/first.last/Desktop/aurora-mcp)
- In Terminal/Command Prompt, while in the
-
Edit the configuration file:
- Open the
mcp.jsonfile in VS Code or any text editor (if it's not already open in TextEdit) - Add this configuration (replace
YOUR_FULL_PATH_HEREwith the path you copied and leave the/build/index.jsafter the path):
{ "mcpServers": { "design-system": { "command": "node", "args": [ "YOUR_FULL_PATH_HERE/build/index.js" ] } } } - Open the
-
Save the file and restart Amazon Q
-
Confirm MCP configuration
- In a new Terminal window, type this command:
qchat mcp list - You should see a reference to the file you just edited (under global:) with a
design-systemitem listed
- In a new Terminal window, type this command:
Step 6: Set Up Your Working Project
Now that the MCP server is configured, you'll want to create a separate workspace for your design system work. This is where you'll generate and organize files before copying them into Interface Designer.
-
Create a new project folder:
- Create a new folder on your Desktop called something like
design-system-workormy-design-project - This folder will be separate from the MCP server folder you downloaded earlier
- Create a new folder on your Desktop called something like
-
Open your working folder in VS Code:
- Launch VS Code
- Go to File → Open Folder
- Select your new working project folder
- This gives you a clean workspace for your design system files
-
Understanding the workflow:
- You'll use Amazon Q chat to query the design system and generate component code
- Amazon Q will provide you with SAIL code snippets
- You can save these snippets as files in your VS Code project for reference
- When ready, you'll copy and paste the final code into Interface Designer
-
Organize your workspace:
- Consider creating folders like:
components/- for individual component fileslayouts/- for layout patternsexamples/- for code examples and variationsnotes/- for design decisions and documentation
- Consider creating folders like:
Step 7: Test It Out
- Open Amazon Q chat (type
q chatin Terminal) - Try asking questions like:
- "What design system categories are available?"
- "Show me all components in the components category"
- "Search the design system for cards"
- "Check the status of documentation sources" (to see if internal docs are enabled)
- "Get details about the cards component including internal documentation" (if you have internal access)
Step 8: Internal Documentation Setup (Optional)
If you need access to internal documentation, follow these additional steps:
Prerequisites
- Access to the internal documentation repository
- Permission to create GitHub Personal Access Tokens for private repositories
Setup Steps
-
Get access to internal repository:
- Contact your team lead to get access to the internal documentation repository
- The repository is typically named something like
aurora-internal
-
Create internal documentation token:
- Go to GitHub Settings > Personal access tokens > Fine-grained tokens
- Create a new token with access to the internal repository
- Set the same permissions as your public token (Contents: Read, Metadata: Read)
-
Update your .env file:
# Add these lines to your existing .env file ENABLE_INTERNAL_DOCS=true INTERNAL_DOCS_TOKEN=your_internal_token_here -
Rebuild and test:
npm run buildTest with Amazon Q:
- "Check the status of documentation sources"
- You should see both PUBLIC and INTERNAL sources listed
Using Internal Documentation
Once set up, you can access internal documentation by:
- Adding "including internal documentation" to your queries
- Using specific internal component names
- Searching within internal documentation only
Example queries:
- "Get details about the admin-panel component including internal documentation"
- "Search for 'internal' components in internal documentation only"
Troubleshooting
If Amazon Q can't find the server:
- Double-check that the path in your config file is correct and absolute (starts with
/on Mac orC:\on Windows) - Make sure you ran
npm run buildsuccessfully - Restart Amazon Q completely
If npm commands don't work:
- Install Node.js from nodejs.org
- Restart your Terminal/Command Prompt after installation
If internal documentation isn't working:
- Verify
ENABLE_INTERNAL_DOCS=trueis set in your .env file - Check that
INTERNAL_DOCS_TOKENhas the correct permissions - Test the token manually by visiting the repository in your browser
- Use "Check the status of documentation sources" to verify both sources are enabled
If you see "Authentication required" errors:
- Your internal documentation token may have expired
- Verify the token has access to the correct repository
- Try regenerating the token with the same permissions
Need help?
- Check the main README.md file for more detailed troubleshooting
- See Migration Guide for upgrading from single-source setup
- See Configuration Guide for advanced configuration options
- The configuration file path must be the complete, absolute path to work properly
What's Next?
Once set up, you can use Amazon Q to explore your design system by asking natural language questions about components, patterns, and layouts. The AI will help you find what you need without having to manually browse through documentation.
Usage with Claude Desktop
-
Make sure you have Claude Desktop installed and up to date
-
Edit the Claude Desktop configuration file:
MacOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%AppData%\Claude\claude_desktop_config.json -
Add the server configuration:
{ "mcpServers": { "design-system": { "command": "node", "args": [ "/ABSOLUTE/PATH/TO/aurora-mcp/build/index.js" ] } } }(Replace
/ABSOLUTE/PATH/TOwith the actual path to this directory) -
Restart Claude Desktop
Troubleshooting
If you encounter issues:
- Check Claude Desktop logs:
tail -n 20 -f ~/Library/Logs/Claude/mcp*.log - Verify your server builds and runs without errors
- Make sure the configuration path is absolute and correct
- Restart Claude Desktop completely
Tools
The server provides the following tools with dual-source support:
Source Management
- get-content-sources: View available documentation sources and their status
- refresh-sources: Manually refresh documentation sources and clear cache
Content Access
- list-categories: Lists all available design system categories
- list-components: Lists all components in a specific category
- get-component-details: Gets detailed information about a specific component with source attribution
includeInternal: Access internal documentation (default: false)sourceOnly: Filter by specific source ("public", "internal", "all")
- search-design-system: Searches across all components by keyword with source filtering
includeInternal: Include internal documentation in searchsourceOnly: Filter results by specific source
For detailed API documentation, see API Guide.
Example Queries
Basic Usage (Public Documentation)
- "What design system categories are available?"
- "Show me all components in the 'layouts' category"
- "Get details about the 'cards' component"
- "Search the design system for 'navigation'"
Dual-Source Usage (Public + Internal)
- "Check the status of documentation sources"
- "Get details about the 'cards' component including internal documentation"
- "Search for 'internal' components in internal documentation only"
- "Show me all components, including internal ones"
- "Refresh the documentation sources"
Advanced Filtering
// Public users - default behavior
"Get details about the cards component"
// Internal users - access internal documentation
"Get details about the cards component with internal documentation included"
// Search only internal documentation
"Search for 'widget' in internal documentation only"
// Check what sources are available
"What documentation sources are available?"
Servidores relacionados
Alpha Vantage MCP Server
patrocinadorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
MCP WordPress Server
A comprehensive MCP server for managing WordPress sites, featuring a wide range of tools for performance monitoring, caching, and more.
Context Portal MCP (ConPort)
A server for managing structured project context using SQLite, with support for vector embeddings for semantic search and Retrieval Augmented Generation (RAG).
OpenTelemetry Collector MCP Server
An MCP server for dynamically configuring OpenTelemetry Collectors, including receivers, processors, and exporters.
App Store Rejections MCP
Catch App Store rejections before they happen
BCMS MCP
Give me a one - two sentence description of the BCMS MCP # MCP The BCMS Model Context Protocol (MCP) integration enables AI assistants like Claude, Cursor, and other MCP-compatible tools to interact directly with your BCMS content. This allows you to create, read, and update content entries, manage media files, and explore your content structure—all through natural language conversations with AI. ## What is MCP? The [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) is an open standard developed by Anthropic that allows AI applications to securely connect to external data sources and tools. With BCMS MCP support, you can leverage AI assistants to: - Query and explore your content structure - Create new content entries with AI-generated content - Update existing entries - Manage your media library - Get intelligent suggestions based on your content model --- ## Getting Started ### Prerequisites 1. A BCMS account with an active instance 2. An MCP key with appropriate permissions 3. An MCP-compatible client (Claude Desktop, Cursor, or any MCP client) ### Step 1: Create an MCP Key 1. Navigate to your BCMS dashboard 2. Go to Settings → MCP 3. Click Create MCP Key 4. Configure the permissions for templates you want the AI to access:GET: Read entries 5. POST: Create entries 6. PUT: Update entries 7. DELETE: Delete entries Note: Right now, MCP only supports creating, reading and updating content. ### Step 2: Configure Your MCP Client You can find full instructions for integrating BCMS with your AI tools right inside BCMS, on the MCP page. But in general, installing BCMS MCP works in a standard way: ``` { "mcpServers": { "bcms": { "url": "https://app.thebcms.com/api/v3/mcp?mcpKey=YOUR_MCP_KEY" } } } ``` ## Available Tools Once connected, your AI assistant will have access to the following tools based on your MCP key permissions: ### Content Discovery #### list_templates_and_entries Lists all templates and their entries that you have access to. This is typically the first tool to call when exploring your BCMS content. Returns: - Template IDs, names, and slugs - Entry IDs with titles and slugs for each language Example prompt: "Show me all the templates and entries in my BCMS" --- ### Entry Management #### list_entries_for_{templateId} Retrieves all entries for a specific template with full content data. A separate tool is generated for each template you have access to. Returns: - Complete entry data including all meta fields - Content in all configured languages - Entry statuses Example prompt: "List all blog posts from my Blog template" --- #### create_entry_for_{templateId} Creates a new entry for a specific template. The input schema is dynamically generated based on your template's field structure. Input: - statuses: Array of status assignments per language - meta: Array of metadata for each language (title, slug, custom fields) - content: Array of content nodes for each language Example prompt: "Create a new blog post titled 'Getting Started with BCMS' with a brief introduction paragraph" --- #### update_entry_for_{templateId} Updates an existing entry for a specific language. Input: - entryId: The ID of the entry to update - lng: Language code (e.g., "en") - status: Optional status ID - meta: Updated metadata - content: Updated content nodes Example prompt: "Update the introduction paragraph of my 'Getting Started' blog post" --- ### Media Management #### list_all_media Lists all media files in your media library. Returns: - Media IDs, names, and types - File metadata (size, dimensions for images) - Parent directory information Example prompt: "Show me all images in my media library" --- #### list_media_dirs Lists the directory structure of your media library. Returns: - Hierarchical directory structure - Directory IDs and names Example prompt: "Show me the folder structure of my media library" --- #### create-media-directory Creates a new directory in your media library. Input: - name: Name of the directory - parentId: Optional parent directory ID (root if not specified) Example prompt: "Create a new folder called 'Blog Images' in my media library" --- #### request-upload-media-url Returns a URL you use to upload a file (for example via POST with multipart form data), which avoids pushing large binaries through the MCP tool payload. You still need a valid file name and MIME type when uploading, as described in the tool response. Availability: Only when the MCP key has Can mutate media enabled. Example prompt: “Give me an upload URL for a new hero image, then tell me how to upload it.” Input: - fileName: Name of the file with extension - fileData: Base64-encoded file data (with data URI prefix) - parentId: Optional parent directory ID Example prompt: "Upload this image to my Blog Images folder" --- ### Linking Tools #### get_entry_pointer_link Generates an internal BCMS link to an entry for use in content. Input: - entryId: The ID of the entry to link to Returns: - Internal link format: entry:{entryId}@*_{templateId}:entry Example prompt: "Get me the internal link for the 'About Us' page entry" --- #### get_media_pointer_link Generates an internal BCMS link to a media item for use in content. Input: - mediaId: The ID of the media item Returns: - Internal link format: media:{mediaId}@*_@*_:entry Example prompt: "Get the link for the hero image so I can use it in my blog post" --- ## Content Structure ### Entry Content Nodes When creating or updating entries, content is structured as an array of nodes. Supported node types include: Type Description paragraph Standard text paragraph heading Heading (h1-h6) bulletList Unordered list orderedList Numbered list listItem List item codeBlock Code block with syntax highlighting blockquote Quote block image Image node widget Custom widget with props ### Example Content Structure ``` { "content": [ { "lng": "en", "nodes": [ { "type": "heading", "attrs": { "level": 1 }, "content": [ { "type": "text", "text": "Welcome to BCMS" } ] }, { "type": "paragraph", "content": [ { "type": "text", "text": "This is your first paragraph." } ] } ] } ] } ``` ## Security & Permissions ### MCP Key Scopes Your MCP key controls what the AI can access: - Template Access: Only templates explicitly granted in the MCP key are visible - Operation Permissions: Each template can have independent GET/POST/PUT/DELETE permissions - Media Access: Media operations are controlled separately ### Best Practices 1. Principle of Least Privilege: Only grant the permissions needed for your use case 2. Separate Keys: Create different MCP keys for different purposes or team members 3. Regular Rotation: Periodically rotate your MCP keys ## Use Cases ### Content Creation Workflows Blog Post Creation "Create a new blog post about the benefits of headless CMS. Include an introduction, three main benefits with explanations, and a conclusion. Use the Blog template." Product Updates "Update the price field for all products in the Electronics category to apply a 10% discount" ### Content Exploration Content Audit "List all blog posts that don't have a featured image set" Translation Status "Show me which entries are missing German translations" ### Media Organization Library Cleanup "Show me all unused images in the media library" Folder Setup "Create folder structure for: Products > Categories > Electronics, Clothing, Home" ## Troubleshooting ### Common Issues #### "MCP key not found" - Verify your MCP key format: keyId.keySecret.instanceId - Ensure the MCP key hasn't been deleted or deactivated - Check that you're using the correct instance #### "MCP key does not have access to template" - Review your MCP key permissions in the dashboard - Ensure the required operation (GET/POST/PUT/DELETE) is enabled for the template #### Session Expired - MCP sessions may timeout after periods of inactivity - Simply start a new conversation to establish a fresh session ### Getting Help - Documentation: [thebcms.com/docs](https://thebcms.com/docs) - Support: [[email protected]](mailto:[email protected]) - Community: [Join BCMS Discord](https://discord.com/invite/SYBY89ccaR) for community support ## Technical Reference ### Endpoint POST https://app.thebcms.com/api/v3/mcp?mcpKey={MCP_KEY} ### Transport BCMS MCP uses the Streamable HTTP transport with session management. Sessions are maintained via the mcp-session-id header. ### Response Format All tools return structured JSON responses conforming to the MCP specification with: - content: Array of content blocks - structuredContent: Typed response data ## Rate Limits MCP requests are subject to the same rate limits as API requests: - Requests are tracked per MCP key - Contact support if you need higher limits for production workloads
Futarchy MCP
Interact with the Futarchy protocol on the Solana blockchain.
Universal MCP Server
A universal MCP server with a modular plugin architecture.
MCP OpenAPI Connector
Connect to any OpenAPI-based API with built-in OAuth2 authentication management.
microCMS
Manage content on the microCMS headless CMS using its content and management APIs.
Autoconsent MCP
A server for browser automation to create and test Autoconsent rules for web page consent management.