Sketch Context▌
by jshmllr
Sketch Context connects Sketch design files to dev workflows, enabling easy component extraction and real-time design wi
Bridges Sketch design files with development workflows through dual-component architecture, enabling file parsing, component extraction, layer management, and real-time design element creation directly from natural language commands.
Both formats append explainx.ai attribution and the canonical URL for this MCP server listing.
best for
- / Design-to-code workflows with AI assistants
- / Frontend developers working with Sketch designs
- / Automating design element creation from specs
capabilities
- / Parse Sketch files and extract components
- / List all symbols and layers in designs
- / Create rectangles and text elements via commands
- / Query specific design components and properties
- / Bridge real-time communication between Sketch and IDEs
what it does
Connects Sketch design files to development IDEs like Cursor, allowing AI to read design components and create new design elements from code.
about
Sketch Context is a community-built MCP server published by jshmllr that provides AI assistants with tools and capabilities via the Model Context Protocol. Sketch Context connects Sketch design files to dev workflows, enabling easy component extraction and real-time design wi It is categorized under developer tools, design.
how to install
You can install Sketch Context in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
license
MIT
Sketch Context is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
readme
[!NOTE] This repository has been archived as of February 5, 2026. Please refer to the official Sketch MCP at https://www.sketch.com/docs/mcp-server/
Note: This project was currently in dev/testing phase and was not fully stable.
Sketch Context MCP
<a href="https://glama.ai/mcp/servers/@jshmllr/Sketch-Context-MCP"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@jshmllr/Sketch-Context-MCP/badge" /> </a>A Model Context Protocol (MCP) server for integrating Sketch designs with IDEs such as Cursor, Cline, or Windsurf.
Overview
This tool allows Cursor IDE to access and interpret Sketch design files, enabling AI-powered design-to-code workflows. It works by:
- Providing a server that parses Sketch files (.sketch)
- Implementing the MCP protocol that Cursor or other IDEs use for context
- Allowing you to reference specific components and layers from your Sketch files
- Providing a UI interface for Sketch that communicates with Cursor
- Enabling real-time bidirectional communication between Sketch and Cursor
Components
This project consists of two main components:
- MCP Server: A Node.js server that implements the Model Context Protocol to provide Sketch file data to Cursor IDE
- Sketch Plugin: A Sketch plugin with UI interface that communicates with the MCP server via WebSockets
Available MCP Tools
The server provides the following tools to Cursor:
get_file: Retrieve contents of a Sketch file or specific node within itlist_components: List all components/symbols in a Sketch fileget_selection: Get information about currently selected elementscreate_rectangle: Create new rectangles with specified dimensions and propertiescreate_text: Create new text elements with custom content and styling
These tools enable Cursor to:
- Access and inspect Sketch design files
- Query specific components and layers
- Create and modify design elements through natural language commands
- Maintain real-time synchronization with Sketch
Supported Features
- Local and Cloud Sketch file parsing
- Component/Symbol extraction
- Asset management and automatic downloads
- Selection links support via the Sketch plugin
- Real-time updates via WebSockets and SSE
- Interactive UI for connecting Sketch to Cursor
- Parsing both local and Sketch Cloud-hosted files
- Extracting document structure and component information
- Accessing specific nodes by ID
- Listing all components in a Sketch file
- Creating rectangles, text and other elements via commands from Cursor
UI & Experience Principles
Review the Accessible, Fast, Delightful UI Principles before shipping changes to the plugin or MCP UI. The guide enumerates the MUST/SHOULD/NEVER rules for interaction patterns, accessibility, performance, and visual design to keep user experiences inclusive and resilient.
Getting Started
Prerequisites
- Node.js (v14 or later)
- Sketch (v70 or later)
- Cursor IDE, VS Code or similar
- A Sketch account (local) or use API access (Sketch Cloud files)
Installation
# Install globally
npm install -g sketch-context-mcp
# Run with a local Sketch file
sketch-context-mcp --local-file=/path/to/your/file.sketch
# Run with Sketch Cloud access
sketch-context-mcp --sketch-api-key=<your-sketch-api-key>
Or run directly with npx:
npx sketch-context-mcp --local-file=/path/to/your/file.sketch
Installing the Sketch Plugin
- Download the latest release of the plugin from the releases page
- Double-click the
.sketchpluginfile to install it in Sketch - The plugin will be available in Sketch under Plugins > Sketch Context MCP
Integration with Cursor
To use this with Cursor:
-
Start the MCP server with your Sketch file:
sketch-context-mcp --local-file=/path/to/your/file.sketch -
In Sketch, open the plugin:
- Go to Plugins > Sketch Context MCP > Open MCP Interface
- Enter the server port (default: 3333)
- Click "Connect"
-
In Cursor, connect to the MCP server:
- Go to Settings > Features > Context
- Add a new MCP server with the URL:
http://localhost:3333/sse - Click "Connect"
-
In the Cursor composer, you can now:
- Reference components by ID: "Show me the component with ID 12345"
- List all components: "List all components in the design"
- Get details about specific elements: "Describe the button in the header"
- Create new elements: "Create a rectangle with width 200 and height 100"
Obtaining a Sketch API Key
The Sketch API key is an OAuth access token required for accessing Sketch Cloud-hosted files. Follow these steps to obtain and use the token:
Step 1: Authenticate with Sketch Cloud
Use your Sketch Cloud credentials (email and password) to generate an access token by making a POST request to the authentication endpoint:
curl -X "POST" "https://auth.sketch.cloud/oauth/token" \
-H 'Content-Type: application/json' \
-d '{
"email": "YOUR_EMAIL",
"password": "YOUR_PASSWORD",
"grant_type": "password"
}'
Replace YOUR_EMAIL and YOUR_PASSWORD with your Sketch Cloud account credentials.
Step 2: Access Token
The response will include an access_token. This token serves as your API key for accessing Sketch Cloud-hosted files.
Step 3: Using the Token
For security, it is recommended to pass the token as an environment variable:
export SKETCH_API_KEY=<your-access-token>
Or include it as a command-line argument:
sketch-context-mcp --sketch-api-key=<your-access-token>
Step 4: Refreshing the Token
If your token expires, use the refresh_token provided in the initial response to obtain a new access token.
Security Best Practices
To ensure your API key is secure, follow these guidelines:
-
Do Not Hard-Code the Key: Never hard-code an API key into the application or source code. Instead, use environment variables or secret management tools.
-
Use .env Files for Local Development: Store your API key in a
.envfile and load it using a library likedotenv:SKETCH_API_KEY=<your-access-token>Ensure the
.envfile is added to.gitignoreto avoid accidental exposure. -
Rotate Tokens Regularly: If your token is leaked or compromised, revoke it and generate a new one immediately.
-
Monitor and Audit: Use tools to scan your repository for exposed credentials (e.g., GitHub’s secret scanning feature).
-
Use Short-Lived Tokens: If possible, use short-lived tokens and refresh them as needed to minimize the impact of a leaked token.
How It Works in Sketch-Context-MCP
The Sketch API key is required for accessing Sketch Cloud-hosted files. The server uses this key to authenticate requests to Sketch Cloud and retrieve the necessary design data. The key is passed securely via the Authorization header when making API requests.
Configuration
The server can be configured using either environment variables (via .env file) or command-line arguments. Command-line arguments take precedence over environment variables.
Environment Variables
SKETCH_API_KEY: Your Sketch API access token (required for Sketch Cloud files)PORT: The port to run the server on (default: 3333)LOCAL_SKETCH_PATH: Path to local Sketch file (alternative to --local-file argument)DEBUG_LEVEL: Set logging verbosity (default: 'info')
Command-line Arguments
--version: Show version number--sketch-api-key: Your Sketch API access token--port: The port to run the server on--stdio: Run the server in command mode, instead of default HTTP/SSE--help: Show help menu
Using the Sketch Plugin
Connection Tab
The Connection tab allows you to connect to the Sketch Context MCP server:
- Enter the port number (default is 3333)
- Click "Connect" to establish a WebSocket connection
- Once connected, you'll see a confirmation message with the channel ID
- Follow the instructions for connecting Cursor to the server
Selection Tab
The Selection tab displays information about selected layers in your Sketch document:
- Select one or more layers in your Sketch document
- The selected layers will be displayed in the list
- Click "Copy Selection IDs" to copy the layer IDs to your clipboard
- Use these IDs in Cursor to reference specific layers
About Tab
The About tab provides information about the plugin and how to use it.
Using with Cursor
Once both Sketch and Cursor are connected to the MCP server:
- Select elements in Sketch
- Copy their IDs using the Sketch Context MCP plugin
- In Cursor, reference these elements by their IDs
Example commands in Cursor:
- "Show me the details of the layer with ID 12345"
- "Create a blue rectangle with width 300 and height 200"
- "Add a text layer with the content 'Hello World'"
Troubleshooting
Common Issues
- Connection Errors: Make sure your server is running and the port is accessible
- Authentication Failures: Verify your Sketch API key is correct
- File Parsing Issues: Ensure your Sketch file is valid and not corrupted
- WebSocket Connection Failed: Ensure the port is not blocked by a firewall
Logs
To enable detailed logging, set the DEBUG environment variable:
DEBUG=sketch-mcp:* npx sketch-context-mcp
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
FAQ
- What is the Sketch Context MCP server?
- Sketch Context is a Model Context Protocol (MCP) server profile on explainx.ai. MCP lets AI hosts (e.g. Claude Desktop, Cursor) call tools and resources through a standard interface; this page summarizes categories, install hints, and community ratings.
- How do MCP servers relate to agent skills?
- Skills are reusable instruction packages (often SKILL.md); MCP servers expose live capabilities. Teams frequently combine both—skills for workflows, MCP for APIs and data. See explainx.ai/skills and explainx.ai/mcp-servers for parallel directories.
- How are reviews shown for Sketch Context?
- This profile displays 31 aggregated ratings (sample rows for discoverability plus signed-in user reviews). Average score is about 4.4 out of 5—verify behavior in your own environment before production use.
Use Cases▌
Extended AI Capabilities
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Context Enhancement
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Workflow Automation
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Implementation Guide▌
Prerequisites
- ›Claude Desktop 0.7.0+ or Cursor IDE with MCP support
- ›Basic understanding of MCP architecture and capabilities
- ›Access credentials for integrated services (if required)
- ›Willingness to experiment and iterate on configuration
Time Estimate
15-60 minutes depending on server complexity
Installation Steps
- 1.Install MCP server: npm install -g [package-name] or via GitHub
- 2.Add server configuration to ~/.claude/mcp.json
- 3.Provide required credentials and configuration
- 4.Restart Claude Desktop to load new server
- 5.Test basic functionality with simple prompts
- 6.Explore capabilities and experiment with use cases
- 7.Document successful patterns for reuse
Troubleshooting
- ⚠MCP server not loading: Check config syntax, verify installation
- ⚠Connection errors: Check network, firewall, credentials
- ⚠Feature not working: Read server docs, check required parameters
- ⚠Performance issues: Monitor resource usage, check for network latency
- ⚠Conflicts with other servers: Check port assignments, namespace collisions
Best Practices▌
✓ Do
- +Read server documentation thoroughly before setup
- +Start with simple use cases to validate functionality
- +Test in non-production environment first
- +Monitor resource usage and performance
- +Keep servers updated for bug fixes and new features
- +Document configuration for team members
- +Use environment variables for sensitive configuration
✗ Don't
- −Don't grant overly permissive access to MCP servers
- −Don't skip reading security considerations in docs
- −Don't expose sensitive data without proper controls
- −Don't run untrusted MCP servers without code review
- −Don't ignore error messages—investigate root cause
💡 Pro Tips
- ★Combine multiple MCP servers for powerful workflows
- ★Create custom MCP servers for your specific needs
- ★Share successful configurations with team
- ★Use MCP inspector for debugging
- ★Join MCP community for tips and troubleshooting
Technical Details▌
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
- Model Context Protocol (MCP)
- JSON-RPC 2.0
- stdio or HTTP transport
Compatibility
- Claude Desktop
- Cursor IDE
- Custom MCP clients
When to Use This▌
✓ Use When
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid When
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.
Integration▌
- →Tool composition: Chain multiple MCP tools in workflows
- →Context augmentation: Provide AI with relevant external data
- →Action delegation: Let AI execute tasks on external systems
- →Bidirectional sync: Keep AI context and external systems in sync
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
List & Promote Your MCP Server
Share your MCP server with the developer community
Ratings
4.4★★★★★31 reviews- ★★★★★Ganesh Mohane· Dec 24, 2024
Sketch Context is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
- ★★★★★Nikhil Diallo· Nov 19, 2024
Sketch Context reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
- ★★★★★Rahul Santra· Nov 15, 2024
Sketch Context is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
- ★★★★★Isabella Anderson· Oct 10, 2024
Useful MCP listing: Sketch Context is the kind of server we cite when onboarding engineers to host + tool permissions.
- ★★★★★Pratham Ware· Oct 6, 2024
We evaluated Sketch Context against two servers with overlapping tools; this profile had the clearer scope statement.
- ★★★★★Piyush G· Sep 25, 2024
I recommend Sketch Context for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
- ★★★★★Mei Rao· Sep 17, 2024
We wired Sketch Context into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
- ★★★★★Nikhil Smith· Sep 1, 2024
Strong directory entry: Sketch Context surfaces stars and publisher context so we could sanity-check maintenance before adopting.
- ★★★★★Aditi Harris· Aug 20, 2024
I recommend Sketch Context for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
- ★★★★★Shikha Mishra· Aug 16, 2024
Strong directory entry: Sketch Context surfaces stars and publisher context so we could sanity-check maintenance before adopting.
showing 1-10 of 31