Sanity Agent Toolkit

Collection of resources to help AI agents build better with Sanity. Supports Cursor, Claude Code, VS Code, Lovable, v0, and any other editor/agent compatible with MCP or Agent Skills.

Features

• MCP server: Direct access to your Sanity projects (content, datasets, releases, schemas) and agent rules.
• Agent skills: Comprehensive best practices skills for Sanity development, content modeling, SEO/AEO, and experimentation. Includes 21 integration/topic guides and 26 focused best-practice rules.
• Claude Code plugin: MCP server, agent skills, and slash commands for Claude Code users.
• Cursor plugin: MCP server, agent skills, and commands for the Cursor Marketplace.

Get started

Choose your path based on how you want agents to work with Sanity:

1. MCP server — Give your agent always up-to-date rules and full access to your Sanity projects. No local files to maintain. Works with Cursor, VS Code, Claude Code, Lovable, v0, and other MCP-compatible clients.
2. Agent skills — Install best practices skills for Sanity, content modeling, SEO/AEO, and experimentation. Works with Cursor, Claude Code, and any Agent Skills-compatible agent.
3. Plugin — Install the Sanity plugin for Cursor or Claude Code. Bundles MCP server, agent skills, and commands.
4. Manual installation — Copy the skill references locally for offline use. You'll need to update them yourself.

Option 1: Install MCP server (recommended)

Give agents direct access to Sanity projects and always up-to-date agent rules via the MCP server.

Quick install via Sanity CLI

Run in terminal to detect and configure MCP for Cursor, Claude Code and VS Code automatically:

npx sanity@latest mcp configure

Uses your logged-in CLI user for authentication — no manual tokens or OAuth needed.

Client-specific instructions

{
  "mcpServers": {
    "Sanity": {
      "type": "http",
      "url": "https://mcp.sanity.io"
    }
  }
}

claude mcp add Sanity -t http https://mcp.sanity.io --scope user

{
  "servers": {
    "Sanity": {
      "type": "http",
      "url": "https://mcp.sanity.io"
    }
  }
}

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sanity": {
      "type": "remote",
      "url": "https://mcp.sanity.io",
      "oauth": {}
    }
  }
}

{
  "mcpServers": {
    "Sanity": {
      "command": "npx",
      "args": ["mcp-remote", "https://mcp.sanity.io", "--transport", "http-only"]
    }
  }
}

See the Sanity MCP docs for authorization options and troubleshooting.

Option 2: Install Agent Skills

Install best practices skills that work with any Agent Skills-compatible agent.

npx skills add sanity-io/agent-toolkit

See Option 3 for plugin installation.

Option 3: Install plugin

Install the Sanity plugin to get MCP server, agent skills, and commands.

Claude Code

1. Add the Sanity marketplace:

/plugin marketplace add sanity-io/agent-toolkit

2. Install the plugin:

/plugin install sanity-plugin@sanity-agent-toolkit

3. Verify installation: Ask Claude Code: "which skills do you have access to?"

You should see the Sanity skills listed.

4. Start using: Use natural language and skills activate automatically:

Help me create a blog post schema in Sanity

Review my GROQ query and Next.js Visual Editing setup

Or run /sanity to explore all capabilities.

Cursor

In Cursor chat, run:

/add-plugin sanity

Option 4: Manual installation

Install the skill references locally to teach your editor Sanity best practices:

1. Copy skills/sanity-best-practices/ to your project.
2. (Recommended) Copy AGENTS.md to your project root to act as a knowledge router.

Capabilities

MCP tools

With MCP connected, your AI can use tools like:

• query_documents — run GROQ queries directly
• create_documents_from_json / create_documents_from_markdown — create draft documents
• patch_document_from_json / patch_document_from_markdown — surgical edits to existing documents
• publish_documents / unpublish_documents — manage document lifecycle
• deploy_schema / get_schema — deploy and inspect schemas
• create_version — create version documents for releases
• generate_image / transform_image — AI image generation and editing
• search_docs / read_docs — search and read Sanity documentation
• list_sanity_rules / get_sanity_rules — load agent rules on demand

See the full list of available tools.

Agent skills

Best practices skills that agents like Claude Code, Cursor, GitHub Copilot, etc. can discover and use automatically. Skills follow the Agent Skills format. See Option 2 for installation.

Getting started flow

The onboarding guide follows three phases:

1. Studio & Schema — Set up Sanity Studio and define your content model
2. Content — Import existing content or generate placeholder content via MCP
3. Frontend — Integrate with your application (framework-specific)

Just say: "Get started with Sanity" to begin.

Slash commands (Claude Code)

Repository structure

Note: The reference files in skills/sanity-best-practices/references/ are the canonical content for the Sanity MCP server's list_sanity_rules / get_sanity_rules tools. Each file must have valid name and description frontmatter — rule names are derived from filenames (e.g., nextjs.md → nextjs).

sanity-io/agent-toolkit/
├── AGENTS.md                      # Knowledge router & agent behavior
├── README.md                      # This file
├── .claude-plugin/                # Claude Code plugin configuration
│   └── marketplace.json           # Plugin metadata and marketplace config
├── .cursor-plugin/                # Cursor plugin configuration
│   ├── marketplace.json           # Cursor marketplace metadata
│   └── plugin.json                # Per-plugin manifest
├── .mcp.json                      # MCP server configuration
├── assets/                        # Plugin branding
│   └── logo.svg                   # Sanity logo for marketplace display
├── commands/                      # Agent commands
│   ├── sanity.md                  # /sanity help
│   ├── review.md                  # /review
│   ├── typegen.md                 # /typegen
│   └── deploy-schema.md           # /deploy-schema
├── scripts/                       # Validation and CI scripts
│   └── validate-cursor-plugin.mjs # Cursor plugin validator
└── skills/                        # Agent skills (agentskills.io format)
    ├── sanity-best-practices/     # Comprehensive Sanity skill
    │   ├── SKILL.md               # Skill definition and quick reference
    │   └── references/            # Canonical content (22 guides)
    │       ├── get-started.md     # Onboarding guide
    │       ├── nextjs.md          # Next.js integration
    │       ├── groq.md            # GROQ patterns & performance
    │       ├── schema.md          # Schema design & validation
    │       └── ...                # See SKILL.md for full index
    ├── content-modeling-best-practices/      # Modeling guidance + topic references
    ├── seo-aeo-best-practices/               # SEO/AEO guidance + topic references
    └── content-experimentation-best-practices/ # Experiment design + stats references

All skills use references/ for detailed content loaded on demand. The sanity-best-practices references are also the canonical source for the MCP server's Sanity rules.

Resources

• Create Sanity account
• Sanity documentation
• GROQ language reference
• Visual Editing guide
• Sanity TypeGen
• MCP server docs
• Blueprints Infrastructure as Code

Contributing

Found a better pattern? Missing a framework or best practice? Read the contributing guide for how skills work and what makes a good contribution, then:

1. Fork the repo.
2. Install dependencies with npm install.
3. Make your changes in skills/<skill-name>/.
4. Run npm run validate:all to check skill and plugin validity.
5. Submit a PR.

Support

• Sanity Community (Discord)
• GitHub issues

License: MIT