Agent Toolkit
未认领Collection of resources to help AI agents build better with Sanity.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'agent-toolkit' -- 'npx' '-y' 'sanity@latest' 'mcp' 'configure'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
14 个工具中显示 14 个
文档中列出的工具 (14)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
create_documents
create draft documents from structured content, or version documents when a release ID is provided
create_release
/ listreleases — create and inspect Content Releases
create_version
create version documents for releases
deploy_schema
/ getschema — deploy MCP-managed schemas and inspect deployed schemas
deploy_studio
deploy a hosted Studio bound to an MCP-managed schema
generate_image
/ transformimage — AI image generation and editing
get_project_studios
list Studio applications linked to a project
give_feedback
report MCP tool errors, missing capabilities, confusing output, or documentation issues
list_sanity_rules
/ getsanityrules — load agent rules on demand
patch_documents
surgical edits to existing documents; published documents are edited by creating or updating drafts
publish_documents
/ unpublishdocuments — manage document lifecycle
query_documents
run GROQ queries directly
search_docs
/ readdocs — search and read Sanity documentation
whoami
verify the authenticated Sanity user