This guide covers best practices for using AI and Large Language Models (LLMs) to accelerate your development workflow with Paragraph’s API.

​
Quick Context for LLMs

When working with AI assistants like Claude, ChatGPT, or Cursor, you can provide comprehensive API context by sharing our full documentation: 
https://paragraph.com/docs/llms-full.txt
Simply paste this URL or its contents into your LLM conversation to give it complete knowledge of Paragraph’s API endpoints, data models, and capabilities.

​
MCP Server Integration

For a more integrated experience with LLMs, you can set up the Paragraph MCP (Model Context Protocol) server. This allows direct interacttion with the API, and the ability to search documentation.

​
Installation

Run the following command to add the Paragraph MCP server to Claude Code. Other AI clients are similar: 
claude mcp add --transport http paragraph https://paragraph.mintlify.app/mcp
Once configured, Claude Code can:
  • Search Paragraph documentation directly
  • Make API calls with proper authentication
  • Access real-time API information
  • Generate code with up-to-date API knowledge

​
Best Practices for AI-Assisted Development

​
1. Provide Clear Context

When prompting AI tools, include:
  • Specific API endpoints you’re working with
  • Example responses or data structures
  • Your programming language and framework
  • Any authentication requirements

​
2. Validate Generated Code

Always review AI-generated code for:
  • Error Handling: Add proper error handling for API responses
  • Rate Limiting: Implement appropriate rate limiting and retry logic
  • Type Safety: Verify types match the API’s expected request/response formats

​
3. Iterative Development

  • Start with simple API calls and gradually add complexity
  • Test each integration point before moving to the next
  • Use the AI to explain error messages and suggest fixes

​
4. Common Prompting Patterns

​
For API Integration

"Help me integrate Paragraph's [endpoint name] endpoint in [language/framework].
I need to [specific use case]. Include error handling and type definitions."

​
For Debugging

"I'm getting [error message] when calling Paragraph's [endpoint].
Here's my code: [code snippet]. What's wrong?"

​
For Data Modeling

"Based on Paragraph's API, help me create [language] models/interfaces
for [specific data types] with proper type annotations."

​
Example Workflow

  1. Initial Setup: Share the llms-full.txt context with your AI assistant
  2. Describe Your Goal: Explain what you want to build with Paragraph’s API
  3. Generate Boilerplate: Have the AI create initial client setup and authentication
  4. Implement Features: Work through each API endpoint you need
  5. Add Error Handling: Ask the AI to add comprehensive error handling
  6. Create Tests: Generate test cases for your integration
  7. Optimize: Request performance improvements and best practices

​
Troubleshooting

If AI-generated code isn’t working:
  • Verify you’re using the latest API version
  • Check that all required headers are included
  • Ensure proper JSON formatting in request bodies
  • Review rate limits and implement appropriate delays

​
Additional Resources