Sanity MCP Server

Name: Sanity MCP Server
Author: MCP-Mirror

@MCP-Mirror

代码仓库

关于 Sanity MCP Server

Mirror of

#sanity-io #mcp-server #content-management

基本信息

分类

其他

许可证

MIT license

运行时

node

传输方式

stdio

发布者

MCP-Mirror

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "sanity-io_sanity-mcp-server": {
      "command": "npx",
      "args": [
        "sanity",
        "schema",
        "deploy"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Sanity MCP Server?

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

How to use Sanity MCP Server?

First, deploy your schema manifest using npx sanity schema deploy (requires Sanity CLI ≥3.88.1) and obtain your project ID, dataset name, and an API token. Then add the server configuration to your MCP‑compatible application’s settings, specifying the required environment variables (SANITY_PROJECT_ID, SANITY_DATASET, SANITY_API_TOKEN, MCP_USER_ROLE). If you use a Node version manager, ensure Node.js is accessible by creating symlinks (see README for OS‑specific steps).

Key features of Sanity MCP Server?

Content Intelligence: AI explores and understands 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.

Use cases of Sanity MCP Server?

Create, update, translate, or transform documents via conversational AI.
Execute GROQ queries to search and retrieve content programmatically.
Manage content releases: create, schedule, publish, or archive releases.
Perform semantic searches across embeddings indexes.
List and manage datasets, projects, and studio applications.

FAQ from Sanity MCP Server

What permissions does the API token need?

For basic read operations, a viewer role is sufficient. For content management, editor or developer is recommended; advanced operations like managing datasets may require an administrator role.

Is it safe to use this server with a production dataset?

If the token has write access, the AI can perform destructive actions (create, update, delete). Use a read‑only token or test on a development/staging dataset first.

Do I need to deploy the schema manifest?

Yes, the MCP server needs access to your content structure. Run npx sanity schema deploy from your Studio directory before using the server.

Which applications can I use this server with?

It works with any MCP‑compatible application, including Claude Desktop, Cursor IDE, VS Code (with appropriate extensions), and custom MCP apps.

How do I configure the server for my application?

Add a JSON block to your application’s MCP settings with command: "npx", args: ["-y", "@sanity/mcp-server@latest"], and the required environment variables listed in the README.