Ditto provides a Model Context Protocol (MCP) server that allows Claude Desktop, Claude Code, and other AI assistants to search and reference API documentation directly during development. This integration helps you discover best practices, avoid common pitfalls, and get contextual help while coding.Documentation Index
Fetch the complete documentation index at: https://docs.ditto.live/llms.txt
Use this file to discover all available pages before exploring further.
What is MCP?
Model Context Protocol (MCP) is an open standard that enables AI assistants to access external data sources and tools. When you connect an MCP server to your AI assistant, it can search and reference documentation in real-time to provide more accurate and contextual responses.Accessing Dittoโs MCP server
Dittoโs API documentation is accessible via MCP at:- Complete API reference documentation
- Code examples and usage patterns
- Best practices and common anti-patterns
- Configuration guides and troubleshooting tips
Setting up with Claude Desktop
To use Dittoโs MCP server with Claude Desktop:-
Open your Claude Desktop configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
- macOS:
- Add the Ditto MCP server to your configuration:
- Restart Claude Desktop for the changes to take effect.
- Verify the connection by asking Claude about Ditto-specific topics. You should see a small icon indicating that Claude is accessing the Ditto documentation.
Setting up with Claude Code
To use Dittoโs MCP server with Claude Code:- Add the Ditto MCP server using the command line:
- Verify the server was added successfully:
- Restart Claude Code for the changes to take effect.
- Verify the connection by asking Claude about Ditto-specific topics while coding. Claude Code will automatically reference the Ditto documentation when relevant.
Using with ChatGPT
To use Dittoโs MCP server with ChatGPT, youโll need to use a compatible MCP client that works with OpenAIโs API. Several community tools are available:- Install an MCP client that supports OpenAI integration
- Configure the client to connect to
https://docs.ditto.live/mcp - Use the client to interact with ChatGPT while having access to Ditto documentation
MCP support for ChatGPT is still evolving. Check the Model Context Protocol documentation and OpenAIโs documentation for the latest integration options.
Example usage
Once configured, you can ask your AI assistant questions like:- โHow do I set up authentication with Ditto?โ
- โWhatโs the best way to structure my Ditto queries?โ
- โShow me how to implement offline-first sync with Dittoโ
- โWhat are common mistakes when using Dittoโs mesh networking?โ
Benefits
Using Dittoโs MCP integration provides several advantages:- Faster development: Get instant answers without leaving your development environment
- Contextual help: The AI assistant can reference your specific use case against Dittoโs documentation
- Best practices: Discover recommended patterns and avoid common pitfalls
- Up-to-date information: Always access the latest documentation without manual searching
Troubleshooting
If youโre having issues connecting to the MCP server:- Verify your configuration file syntax is correct (valid JSON)
- Ensure you have Node.js installed (required for the
npxcommand) - Check that you have an active internet connection
- Restart your AI assistant application after making configuration changes