Sanity
概览
作者提供的说明(英文原文)
Direct access to your Sanity projects (content, datasets, releases, schemas) and agent rules
PopNx MCP 的三大支柱
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i3 项中通过 3 项依据公开信息检查;尚未扫描代码
- 使用情况i非常新★ –
它能帮你做什么
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
- 连接方式: 在云端运行
- 传输方式: Streamable HTTP
- 分类: 数据库与数据集
安装
选择你使用的 AI 应用,然后复制设置。
安装之前
- 基础检查:3 项中通过 3 项
- 在作者的服务器上运行:你向它提出的内容会经过他们的服务器。
- 注册中心没有列出需要填写的密钥。
你需要
- 在云端运行无需安装任何东西,通过互联网连接
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
- 打开 Settings → Connectors
- 点击 Add custom connector
- 粘贴下面的地址,然后点击 Add
- 如果要求登录,请登录作者的服务
https://mcp.sanity.io在终端中运行这条命令
claude mcp add --transport http www https://mcp.sanity.io或者自己复制设置
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"www": {
"url": "https://mcp.sanity.io"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"www": {
"type": "http",
"url": "https://mcp.sanity.io"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
- 打开网页版 ChatGPT → Settings → Connectors (Apps)
- 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
- 粘贴下面的地址,起个名字,然后保存
- 如果要求登录,请登录作者的服务
https://mcp.sanity.io菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它能做什么
服务器要求先登录,才会列出它的工具。
基础检查i
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月9日
- ✓ 通过
作者与仓库一致
注册名称已通过域名 www.sanity.io 验证(注册中心会核实域名所有权)
- … 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
- … 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
- ✓ 通过
端点有响应
在 287 毫秒内响应(HTTP 401)
- ✓ 通过
使用 OAuth 登录
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
- … 尚未检查
工具描述中没有隐藏指令
尚未检查;我们会在检查端点时读取工具列表
与“数据库与数据集”中的其他服务器比较i
- 星标数多于此分类中其他 1153 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 1153 个服务器的 86% 更新
- 基础检查结果等于或优于此分类中其他 1153 个服务器的 100%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
常见问题
Sanity 安全吗?
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端?
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
它还在维护吗?
GitHub 仓库最后更新于–,最新版本(2.46.0)于5天前进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
有什么可以替代它?
同一分类中有:Supabase, MongoDB MCP Server, Elasticsearch MCP Server
替代选择
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Sanity Agent Toolkit
Collection of resources to help AI agents build better with Sanity. Supports Cursor, Claude Code, Codex, VS Code, Lovable, v0, Replit, OpenCode, 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 25 integration/topic guides and 26 focused best-practice rules.
- Agent Plugin:
plugin.json,skills/, andmcp.jsoncomponents for any Agent Plugins-compatible client. - Claude Code plugin: MCP server, agent skills, and slash commands for Claude Code users. Available on the official Anthropic plugin marketplace.
- Cursor plugin: MCP server, agent skills, and commands on the Cursor Marketplace.
- Codex plugin: MCP server and agent skills for OpenAI Codex users.
Get started
Choose your path based on how you want agents to work with Sanity:
- 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, Replit, OpenCode, and other MCP-compatible clients.
- 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.
- Plugin — Install the Sanity plugin for Cursor, Claude Code, or any Agent Plugins-compatible client. Bundles MCP server, agent skills, and commands.
- 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
Cursor
One-click install:
Or manually: Open Command Palette (Cmd+Shift+P / Ctrl+Shift+P) → View: Open MCP Settings → + New MCP Server → add to mcp.json:
{
"mcpServers": { "Sanity": { "type": "http", "url": "https://mcp.sanity.io" } } }
</details>
Claude Code
Run in terminal. Authenticate with OAuth on next launch:
claude mcp add Sanity -t http https://mcp.sanity.io --scope user
Codex
Run in terminal. Authenticate with OAuth on next launch:
codex mcp add Sanity --url https://mcp.sanity.io
Or manually add to ~/.codex/config.toml:
[mcp_servers.Sanity]
url = "https://mcp.sanity.io"
</details>
VS Code
Open Command Palette (Cmd+Shift+P / Ctrl+Shift+P) → MCP: Open User Configuration → add:
{
"servers": { "Sanity": { "type": "http", "url": "https://mcp.sanity.io" } } }
</details>
Lovable
Sanity is available as a prebuilt chat connector in Lovable:
- Open Connectors → Chat connectors
- Select Sanity
- Click Connect and sign in to authorize your Sanity account
In your next prompt, reference your Sanity project or ask the agent to read your schema.
See the Lovable MCP documentation or Sanity + Lovable guide for more details.
v0
In the prompt input field, click Prompt Tools → MCPs → Add New → Select Sanity → Authorize → Authenticate with OAuth.
Replit
Go to Integrations Page → scroll to MCP Servers for Replit Agent → Add MCP server → Enter Sanity as name and https://mcp.sanity.io as Server URL → Test & Save → Authenticate with OAuth.
OpenCode
Add to your opencode.json:
{
"$schema": "https://opencode.ai/config.json", "mcp": { "sanity": { "type": "remote", "url": "https://mcp.sanity.io", "oauth": {} } } }
Then run: `opencode mcp auth sanity`
Other clients
For any MCP-compatible client, add https://mcp.sanity.io as the server URL.
If your client doesn't support remote MCP servers, use a proxy like mcp-remote:
{
"mcpServers": { "Sanity": { "command": "npx", "args": ["mcp-remote", "https://mcp.sanity.io", "--transport", "http-only"] } } }
</details>
Authorization and troubleshooting
Manual MCP configuration uses OAuth by default. You can use token auth instead by setting an Authorization: Bearer header in the MCP config. If authentication fails after CLI setup, rerun npx sanity@latest mcp configure and restart your MCP client. For OAuth reset issues, Cursor provides Cursor: Clear All MCP Tokens and VS Code provides Authentication: Remove Dynamic Authentication Providers.
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. Available on the Claude Code marketplace, Cursor Marketplace, or from this repo as an Agent Plugin.
Claude Code
The Sanity plugin is listed on the official Anthropic plugin marketplace. The official marketplace (claude-plugins-official) is pre-registered when you start Claude Code — you do not need to add a custom marketplace.
Install from Claude Code:
/plugin install sanity@claude-plugins-official
If the plugin is not found, refresh the marketplace catalog and retry:
/plugin marketplace update claude-plugins-official
Then run /reload-plugins to activate without restarting.
Alternative: interactive install
- Run
/pluginand open the Discover tab - Search for Sanity
- Review what the plugin will install — commands, skills, hooks, and MCP servers — before confirming (Anthropic recommends reviewing plugin permissions and source before installing)
- Choose an installation scope:
- User (default): all projects on this machine
- Project: shared with collaborators via
.claude/settings.json - Local: this repository only
- Run
/reload-pluginsto activate without restarting
Verify installation: Ask Claude Code: "which skills do you have access to?"
You should see the Sanity skills listed.
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
Install from the Cursor Marketplace by running this in Cursor chat:
/add-plugin sanity
Verify installation: Ask Cursor: "which skills do you have access to?"
You should see the Sanity skills listed.
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
Codex
- Add the Sanity marketplace:
codex plugin marketplace add sanity-io/agent-toolkit
- Install the plugin from Codex's plugin directory (select the Sanity Agent Toolkit marketplace, then install Sanity).
- Restart Codex. Verify by asking: "which skills do you have access to?" — you should see the Sanity skills listed.
Option 4: Manual installation
Install the skill references locally to teach your editor Sanity best practices:
- Copy
skills/sanity-best-practices/to your project. - (Recommended) Copy
AGENTS.mdto 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 directlycreate_documents— create draft documents from structured content, or version documents when a release ID is providedpatch_documents— surgical edits to existing documents; published documents are edited by creating or updating draftspublish_documents/unpublish_documents— manage document lifecycledeploy_schema/get_schema— deploy MCP-managed schemas and inspect deployed schemasdeploy_studio— deploy a hosted Studio bound to an MCP-managed schemacreate_release/list_releases— create and inspect Content Releasescreate_version— create version documents for releasesgenerate_image/transform_image— AI image generation and editingwhoami— verify the authenticated Sanity userget_project_studios— list Studio applications linked to a projectsearch_docs/read_docs— search and read Sanity documentationlist_sanity_rules/get_sanity_rules— load agent rules on demandgive_feedback— report MCP tool errors, missing capabilities, confusing output, or documentation issues
MCP-managed schemas are resolved before Studio-deployed and legacy schemas. If you deploy schema changes with deploy_schema, redeploy any matching MCP-managed Studio with deploy_studio so it picks up the latest schema. generate_image, transform_image, and create_version with an instruction consume Sanity AI credits.
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.
| Skill | Description |
|---|---|
| sanity-best-practices | GROQ performance, schema design, Visual Editing, images, Portable Text, Studio, TypeGen, localization, migrations, and framework integration guides |
| content-modeling-best-practices | Structured content principles: separation of concerns, references vs embedding, content reuse |
| seo-aeo-best-practices | SEO/AEO with EEAT principles, structured data (JSON-LD), technical SEO patterns |
| content-experimentation-best-practices | A/B testing methodology, statistical foundations, experiment design |
| sanity-singletons | First-class singleton documents via document.singletons, Structure helpers, and migrating from u
只显示了开头部分;其余内容请在仓库中阅读