Sanity MCP Server

Official
by sanity-io

Integrations

  • Runs as a Node.js application, requiring proper Node.js environment setup to function correctly with MCP-compatible applications.

  • Provides special configuration instructions for users of Node Version Manager to ensure the MCP server can access Node.js properly.

  • Enables AI-powered tools for content operations in Sanity CMS, allowing users to create, update, and manage documents, handle release management, perform semantic searches, and access schema information through natural language instructions.

Sanity MCP Server

Transform your content operations with AI-powered tools for Sanity. Create, manage, and explore your content through natural language conversations in your favorite AI-enabled editor.

Sanity MCP Server implements the Model Context Protocol to connect your Sanity projects with AI tools like Claude, Cursor, and VS Code. It enables AI models to understand your content structure and perform operations through natural language instructions.

✨ Key Features

  • 🤖 Content Intelligence: Let AI explore and understand your content library
  • 🔄 Content Operations: Automate tasks through natural language instructions
  • 📊 Schema-Aware: AI respects your content structure and validation rules
  • 🚀 Release Management: Plan and organize content releases effortlessly
  • 🔍 Semantic Search: Find content based on meaning, not just keywords

Table of Contents

🔌 Quickstart

Prerequisites

Before you can use the MCP server, you need to:

  1. Deploy your Sanity Studio with schema manifestThe MCP server needs access to your content structure to work effectively. Deploy your schema manifest using one of these approaches:
    # Option A: If you have the CLI installed globally npm install -g sanity cd /path/to/studio sanity schema deploy # Option B: Update your Studio cd /path/to/studio npm update sanity npx sanity schema deploy
    When running in CI environments without Sanity login, you'll need to provide an auth token:
    SANITY_AUTH_TOKEN=<token> sanity schema deploy

    Note

    Schema deployment requires Sanity CLI version 3.88.1 or newer.

  2. Get your API credentials
    • Project ID
    • Dataset name
    • API token with appropriate permissions

This MCP server can be used with any application that supports the Model Context Protocol. Here are some popular examples:

Add configuration for the Sanity MCP server

To use the Sanity MCP server, add the following configuration to your application's MCP settings:

{ "mcpServers": { "sanity": { "command": "npx", "args": ["-y", "@sanity/mcp-server@latest"], "env": { "SANITY_PROJECT_ID": "your-project-id", "SANITY_DATASET": "production", "SANITY_API_TOKEN": "your-sanity-api-token" } } } }

The exact location of this configuration will depend on your application:

ApplicationConfiguration Location
Claude DesktopClaude Desktop configuration file
CursorWorkspace or global settings
VS CodeWorkspace or user settings (depends on extension)
Custom AppsRefer to your app's MCP integration docs

You don't get it to work? See the section on Node.js configuration.

🛠️ Available Tools

Context & Setup

  • get_initial_context – IMPORTANT: Must be called before using any other tools to initialize context and get usage instructions.
  • get_sanity_config – Retrieves current Sanity configuration (projectId, dataset, apiVersion, etc.)

Document Operations

  • create_document – Create a new document with AI-generated content based on instructions
  • update_document – Update an existing document with AI-generated content based on instructions
  • patch_document - Apply direct patch operations to modify specific parts of a document without using AI generation
  • query_documents – Execute GROQ queries to search for and retrieve content
  • document_action – Perform document actions like publishing, unpublishing, or deleting documents

Release Management

  • list_releases – List content releases, optionally filtered by state
  • create_release – Create a new content release
  • edit_release – Update metadata for an existing release
  • schedule_release – Schedule a release to publish at a specific time
  • release_action – Perform actions on releases (publish, archive, unarchive, unschedule, delete)

Version Management

  • create_version – Create a version of a document for a specific release
  • discard_version – Delete a specific version document from a release
  • mark_for_unpublish – Mark a document to be unpublished when a specific release is published

Dataset Management

  • get_datasets – List all datasets in the project
  • create_dataset – Create a new dataset
  • update_dataset – Modify dataset settings

Schema Information

  • get_schema – Get schema details, either full schema or for a specific type
  • list_schema_ids – List all available schema IDs

GROQ Support

  • get_groq_specification – Get the GROQ language specification summary
  • list_embeddings_indices – List all available embeddings indices
  • semantic_search – Perform semantic search on an embeddings index

Project Information

  • list_projects – List all Sanity projects associated with your account
  • get_project_studios – Get studio applications linked to a specific project

⚙️ Configuration

The server takes the following environment variables:

VariableDescriptionRequired
SANITY_API_TOKENYour Sanity API token
SANITY_PROJECT_IDYour Sanity project ID
SANITY_DATASETThe dataset to use
SANITY_API_HOSTAPI host (defaults to https://api.sanity.io)
MCP_USER_ROLEDetermines tool access level (developer or editor)

Warning

Using AI with Production Datasets When configuring the MCP server with a token that has write access to a production dataset, please be aware that the AI can perform destructive actions like creating, updating, or deleting content. This is not a concern if you're using a read-only token. While we are actively developing guardrails, you should exercise caution and consider using a development/staging dataset for testing AI operations that require write access.

🔑 API Tokens and Permissions

The MCP server requires appropriate API tokens and permissions to function correctly. Here's what you need to know:

  1. Generate a Robot Token:
    • Go to your project's management console: Settings > API > Tokens
    • Click "Add new token"
    • Create a dedicated token for your MCP server usage
    • Store the token securely - it's only shown once!
  2. Required Permissions:
    • The token needs appropriate permissions based on your usage
    • For basic read operations: viewer role is sufficient
    • For content management: editor or developer role recommended
    • For advanced operations (like managing datasets): administrator role may be needed
  3. Dataset Access:
    • Public datasets: Content is readable by unauthenticated users
    • Private datasets: Require proper token authentication
    • Draft and versioned content: Only accessible to authenticated users with appropriate permissions
  4. Security Best Practices:
    • Use separate tokens for different environments (development, staging, production)
    • Never commit tokens to version control
    • Consider using environment variables for token management
    • Regularly rotate tokens for security

👥 User Roles

The server supports two user roles:

  • developer: Access to all tools
  • editor: Content-focused tools without project administration

📦 Node.js Environment Setup

Important for Node Version Manager Users: If you use nvm, mise, fnm, nvm-windows or similar tools, you'll need to follow the setup steps below to ensure MCP servers can access Node.js. This is a one-time setup that will save you troubleshooting time later. This is an ongoing issue with MCP servers.

🛠 Quick Setup for Node Version Manager Users

  1. First, activate your preferred Node.js version:
    # Using nvm nvm use 20 # or your preferred version # Using mise mise use node@20 # Using fnm fnm use 20
  2. Then, create the necessary symlinks (choose your OS):On macOS/Linux:
    sudo ln -sf "$(which node)" /usr/local/bin/node && sudo ln -sf "$(which npx)" /usr/local/bin/npx

    Note

    While using sudo generally requires caution, it's safe in this context because:

    • We're only creating symlinks to your existing Node.js binaries
    • The target directory (/usr/local/bin) is a standard system location for user-installed programs
    • The symlinks only point to binaries you've already installed and trust
    • You can easily remove these symlinks later with sudo rm
    On Windows (PowerShell as Administrator):
    New-Item -ItemType SymbolicLink -Path "C:\Program Files\nodejs\node.exe" -Target (Get-Command node).Source -Force New-Item -ItemType SymbolicLink -Path "C:\Program Files\nodejs\npx.cmd" -Target (Get-Command npx).Source -Force
  3. Verify the setup:
    # Should show your chosen Node version /usr/local/bin/node --version # macOS/Linux "C:\Program Files\nodejs\node.exe" --version # Windows

🤔 Why Is This Needed?

MCP servers are launched by calling node and npx binaries directly. When using Node version managers, these binaries are managed in isolated environments that aren't automatically accessible to system applications. The symlinks above create a bridge between your version manager and the system paths that MCP servers use.

🔍 Troubleshooting

If you switch Node versions often:

  • Remember to update your symlinks when changing Node versions
  • You can create a shell alias or script to automate this:
    # Example alias for your .bashrc or .zshrc alias update-node-symlinks='sudo ln -sf "$(which node)" /usr/local/bin/node && sudo ln -sf "$(which npx)" /usr/local/bin/npx'

To remove the symlinks later:

# macOS/Linux sudo rm /usr/local/bin/node /usr/local/bin/npx # Windows (PowerShell as Admin) Remove-Item "C:\Program Files\nodejs\node.exe", "C:\Program Files\nodejs\npx.cmd"

💻 Development

Install dependencies:

pnpm install

Build and run in development mode:

pnpm run dev

Build the server:

pnpm run build

Run the built server:

pnpm start

Debugging

For debugging, you can use the MCP inspector:

npx @modelcontextprotocol/inspector -e SANITY_API_TOKEN=<token> -e SANITY_PROJECT_ID=<project_id> -e SANITY_DATASET=<ds> -e MCP_USER_ROLE=developer node path/to/build/index.js

This will provide a web interface for inspecting and testing the available tools.

Related MCP Servers

  • A
    security
    A
    license
    A
    quality
    Enables AI agents to manage issues, projects, and teams on the Linear platform programmatically.
    Last updated -
    7
    123
    22
    JavaScript
    MIT License
    • Apple
  • -
    security
    A
    license
    -
    quality
    Facilitates integration with Claude Desktop to run AI agents and execute purchased actions without code, leveraging the Model Context Protocol framework.
    Last updated -
    1
    TypeScript
    GPL 3.0
  • -
    security
    A
    license
    -
    quality
    Enables AI agents and assistants like Goose or Claude to interact with VS Code through the Model Context Protocol.
    Last updated -
    14
    TypeScript
    Apache 2.0
    • Apple
  • -
    security
    F
    license
    -
    quality
    Enables AI assistants to interact with Metabase, providing access to dashboards, questions, databases, and tools for executing queries and viewing data through natural language.
    Last updated -
    JavaScript
    • Apple

View all related MCP servers

ID: s8v5wceait