AI tooling

AI Tooling

Learn how to use Schematic with AI development tools and assistants to accelerate your integration and development workflow.

Overview

Schematic provides several AI tooling options to help developers integrate Schematic faster and work more efficiently with AI coding assistants. These tools enable AI assistants to understand Schematic’s API, generate integration code, and interact with your Schematic account directly.

Schematic AI Skills

Schematic AI Skills provide context and capabilities for AI coding assistants to help you integrate Schematic into your codebase. These skills are available for different parts of your application. All skills can be found in the Schematic AI Tools GitHub Repository.

Frontend Repository

AI skills for frontend development help you integrate Schematic’s React, Vue, and other frontend SDKs. Use these skills to:

  • Generate code for feature flag checks in your UI components
  • Create usage tracking implementations
  • Build customer portal integrations
  • Implement plan-based UI rendering

Backend Repository

AI skills for backend development assist with server-side Schematic integrations. Use these skills to:

  • Generate API integration code for your backend services
  • Create middleware for entitlement enforcement
  • Implement usage tracking endpoints
  • Build admin interfaces for plan management

Components

AI skills for Schematic Components help you integrate and customize UI components like:

  • Customer Portal
  • Pricing Tables
  • Checkout flows
  • Usage meters

Model Context Protocol (MCP)

Schematic hosts an MCP server at https://api.schematichq.com/mcp. Any MCP-compatible AI assistant can connect to it to interact with your Schematic account directly:

  • Query company information and plans
  • Check feature usage and entitlements
  • Manage company overrides
  • Create and update features and plans
  • Analyze usage patterns

Common Use Cases

The MCP integration is particularly useful for:

  • Code generation - AI assistants can query your actual Schematic data to generate accurate integration code
  • Troubleshooting - Ask AI assistants about specific companies, plans, or features in your account
  • Data analysis - Use natural language queries to analyze usage patterns and customer data
  • Plan management - Let AI assistants help you create and modify plans based on your requirements

Connect with OAuth

Clients that support MCP OAuth (such as Claude) can connect with your Schematic user account — no API key needed.

In Claude, go to Settings > Connectors > Add custom connector and enter https://api.schematichq.com/mcp as the URL. When you connect, Schematic asks you to sign in, pick an environment, and choose read-only or read and write access. Write tools also respect your team member permissions: a grant can never do more than you can do in the Schematic app, and permission changes take effect immediately.

In Claude Code:

$claude mcp add --transport http schematic https://api.schematichq.com/mcp

Then run /mcp to sign in.

Connect with an API key

Clients can also authenticate with a Schematic secret API key as a bearer token:

$claude mcp add --transport http schematic https://api.schematichq.com/mcp \
>  --header "Authorization: Bearer your-secret-api-key"

Read-only API keys can use only the read tools.

Example MCP queries:

  • “What plan is company Acme Corp on?”
  • “Show me feature usage for the ‘api_calls’ feature across all companies”
  • “Create a company override to enable ‘beta_features’ for company comp_123”