MCP server
by jshmllr
Sketch Context connects Sketch design files to dev workflows, enabling easy component extraction and real-time design wi
Connects Sketch design files to development IDEs like Cursor, allowing AI to read design components and create new design elements from code.
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.
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.
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.
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
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
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
Share your MCP server with the developer community
Sketch Context is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
Sketch Context reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
Sketch Context is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
Useful MCP listing: Sketch Context is the kind of server we cite when onboarding engineers to host + tool permissions.
We evaluated Sketch Context against two servers with overlapping tools; this profile had the clearer scope statement.
I recommend Sketch Context for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
We wired Sketch Context into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Strong directory entry: Sketch Context surfaces stars and publisher context so we could sanity-check maintenance before adopting.
I recommend Sketch Context for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
Strong directory entry: Sketch Context surfaces stars and publisher context so we could sanity-check maintenance before adopting.
showing 1-10 of 31
[!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.
A Model Context Protocol (MCP) server for integrating Sketch designs with IDEs such as Cursor, Cline, or Windsurf.
This tool allows Cursor IDE to access and interpret Sketch design files, enabling AI-powered design-to-code workflows. It works by:
This project consists of two main components:
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 stylingThese tools enable Cursor to:
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.
# 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
.sketchplugin file to install it in SketchTo 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:
In Cursor, connect to the MCP server:
http://localhost:3333/sseIn the Cursor composer, you can now:
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:
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.
The response will include an access_token. This token serves as your API key for accessing Sketch Cloud-hosted files.
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>
If your token expires, use the refresh_token provided in the initial response to obtain a new access token.
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 .env file and load it using a library like dotenv:
SKETCH_API_KEY=<your-access-token>
Ensure the .env file is added to .gitignore to 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.
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.
The server can be configured using either environment variables (via .env file) or command-line arguments. Command-line arguments take precedence over 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')--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 menuThe Connection tab allows you to connect to the Sketch Context MCP server:
The Selection tab displays information about selected layers in your Sketch document:
The About tab provides information about the plugin and how to use it.
Once both Sketch and Cursor are connected to the MCP server:
Example commands in Cursor:
To enable detailed logging, set the DEBUG environment variable:
DEBUG=sketch-mcp:* npx sketch-context-mcp
Contributions are welcome! Please feel free to submit a Pull Request.
This project is licensed under the MIT License - see the LICENSE file for details.
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ 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.