Skip to main content

What You'll Build

An AI-powered content management system workflow that uses Continue’s AI agent with Sanity MCP to manage schemas, execute GROQ queries, handle migrations, and maintain documentation - all through simple natural language prompts

Prerequisites

Before starting, ensure you have:
  • Node.js 20+ installed locally
  • A Sanity account and project (free tier works)
  • Basic understanding of content management systems
For all options, first:
1

Install Continue CLI

2

Install Sanity CLI

To use agents in headless mode, you need a Continue API key and proper environment variable configuration.

Getting Started with Sanity

New to Sanity? Follow the Sanity Getting Started Guide to set up your first project.Quick setup:
Key resources:

Sanity MCP Workflow Options

Fastest Path to Success

Skip the manual setup and use our pre-built Sanity Assistant agent that includes the Sanity MCP and optimized content management workflows for more consistent results. You can customize it for your specific needs.
After ensuring you meet the Prerequisites above, you have two paths to get started:
To use the pre-built Sanity Assistant agent, you need either:
  • Continue CLI Pro Plan with the models add-on, OR
  • Your own API keys configured as environment variables
The agent will automatically detect and use your configuration along with the pre-configured Sanity MCP for content operations. Note that OAuth authentication will be required on first use.

Sanity MCP Capabilities

Understanding the Capabilities

Sanity MCP provides comprehensive tools for content management:The MCP integrates seamlessly with your existing Sanity workspace, providing AI-powered assistance for both development and content operations.

Your First MCP Conversation

With everything set up, you’re ready for your first AI-powered content conversation! Try these beginner-friendly starter prompts:

Content Discovery

Content Creation

Content Updates

Content Scheduling

New to MCP? These prompts demonstrate the power of natural language content management. For more examples and detailed explanations, check out the official Sanity MCP blog post.

Content Management Recipes

Now you can use natural language prompts to manage your Sanity content and schemas. The Continue agent automatically calls the appropriate Sanity MCP tools.
Where to run these workflows:
  • IDE Extensions: Use Continue in VS Code, JetBrains, or other supported IDEs
  • Terminal (TUI mode): Run cn to enter interactive mode, then type your prompts
  • CLI (headless mode): Use cn -p "your prompt" for headless commands
Test in Plan Mode First: Before running operations that might make changes, test your prompts in plan mode (see the Plan Mode Guide; press Shift+Tab to switch modes in TUI/IDE). This shows you what the agent will do without executing it.To run any of the example prompts below in headless mode, use cn -p "prompt"
About the —auto flag: The --auto flag enables tools to run continuously without manual confirmation. This is essential for headless mode where the agent needs to execute multiple tools automatically to complete tasks like schema exploration, GROQ execution, and content migration.

Schema Management

Explore Document Types

Review and understand your content schema structure.Prompt:

GROQ Queries

Execute GROQ Queries

Run GROQ queries to fetch and analyze content.Prompt:

Content Operations

Bulk Content Updates

Perform bulk operations on your content.Prompt:

Localization

Add Localization Support

Set up and manage content translations.Prompt:

Content Migration

Migrate Content Structure

Migrate content between different schemas or environments.Prompt:

Documentation Generation

Generate Schema Documentation

Automatically generate documentation for your content model.Prompt:

Content Releases

Manage Content Releases

Work with Sanity’s content release feature.Prompt:

Performance Analysis

Analyze Query Performance

Optimize GROQ queries for better performance.Prompt:

Continuous Content Management with GitHub Actions

This example demonstrates a Continuous AI workflow where content validation and schema checks run automatically in your CI/CD pipeline in headless mode using the Sanity agent config. Consider customizing this agent to add your organization’s specific content governance rules.

Add GitHub Secrets

Navigate to Repository Settings → Secrets and variables → Actions and add:
  • CONTINUE_API_KEY: Your Continue API key from continue.dev/settings/api-keys
  • SANITY_PROJECT_ID: Your Sanity project ID
  • SANITY_DATASET: Your Sanity dataset name (usually “production”)
  • SANITY_API_TOKEN: Your Sanity API token with appropriate permissions
  • MCP_USER_ROLE: Your MCP user role (typically “admin” or “editor”)
The workflow uses the Sanity Assistant Agent with environment variable authentication via Sanity MCP Config. This enables headless mode operation without OAuth browser authentication.

Create Workflow File

This workflow automatically validates your Sanity schemas and content on pull requests using the Continue CLI in headless mode. It checks schema integrity, validates content relationships, and posts a summary report as a PR comment. Create .github/workflows/sanity-content-validation.yml in your repository:
Environment variables enable the MCP to authenticate without OAuth browser prompts. The Sanity MCP Config documentation provides detailed setup instructions for all required variables.

Content Management Best Practices

Implement automated content quality checks using Continue’s rule system. See the Rules deep dive for authoring tips.

Schema Validation

Content Consistency

Query Optimization

Localization Standards

Troubleshooting

Authentication Issues

Schema Not Found

GROQ Query Errors

Migration Conflicts

Verification Steps:
  • Sanity MCP is installed and configured
  • Project is authenticated with Sanity
  • Schema files are present and valid
  • Dataset permissions are correctly configured

What You’ve Built

After completing this guide, you have a complete AI-powered content management system that:
  • ✅ Uses natural language — Simple prompts instead of complex CMS commands
  • ✅ Manages schemas automatically — AI handles schema evolution and migrations
  • ✅ Runs continuously — Automated validation in CI/CD pipelines
  • ✅ Ensures quality — Content checks prevent broken references and invalid data

Continuous AI

Your content management workflow now operates at Level 2 Continuous AI - AI handles routine content operations and schema management with human oversight through review and approval of changes.

Next Steps

  1. Explore your schema - Try the schema exploration prompt on your current project
  2. Run GROQ queries - Use natural language to query your content
  3. Set up CI validation - Add the GitHub Actions workflow to your repo
  4. Create documentation - Generate comprehensive docs for your content model
  5. Optimize performance - Analyze and improve query performance

Additional Resources

Sanity Documentation

Complete Sanity platform documentation

Continue Documentation

Explore Continue documentation and guides

GROQ Documentation

Learn GROQ query language

Sanity MCP Blog Post

Official Sanity MCP introduction with examples

Sanity MCP Setup

Official Sanity MCP documentation