Sanity MCP server
Yes. Sanity publishes 2 official MCP servers: Sanity MCP server and Sanity. They're all hosted. We last checked them on 22 Nov 2026.
Official: answers MCP requests at mcp.sanity.io, on Sanity's own domain sanity.io. Checked 22 Nov 2026. Maintained by Stuart Brameld.
Key facts
As of 22 Nov 2026, the best of Sanity's 2 official MCP servers, Sanity MCP server, scores 85/100 (provisional) on MartechDB's Agent Readiness Index (v1.1). It answered 55 of our 55 checks in the last 90 days and has 60 tools named in its documentation.
How the Agent Readiness Index works · Wrong? Suggest a correction
Sanity MCP server review
85/100
Sanity's MCP server scores 85/100 on MartechDB's Agent Readiness Index: one of the easiest marketing tools to connect an AI agent to.
The good
Hosted by Sanity: connect by URL, with nothing to install
Sign in with your Sanity account: your AI client sets up the sign-in itself, with no API key
Documented, with 60 tools known
Published to the official MCP Registry
Answered 100% of our checks in the last 90 days
The bad
Nothing we've found.
Official MCP servers
Sanity MCP server
- Address
- https://mcp.sanity.io/mcp
- Runs
- Hosted
- Sign-in
- Cost to use
- Most tools use no AI credits; generate_image and transform_image consume AI creditsFrom Sanity's own page
- Official MCP Registry
- Listed
- How we know it's official
-
- Answers MCP requests at mcp.sanity.io, on Sanity's own domain sanity.io.
- Documentation
- www.sanity.io/docs/ai/mcp-server
- Tools
- 60 tools · from Sanity's documentation
- First seen
- 1 Oct 2026
- Last checked
-
Reachable ·
16 Nov 2026: reachable17 Nov 2026: reachable18 Nov 2026: reachable19 Nov 2026: reachable20 Nov 2026: reachable21 Nov 2026: reachable22 Nov 2026: reachable
- Uptime
- 100% · 55 of 55 checks reachable since 1 Oct 2026
Sanity MCP server tools (60)
The server needs sign-in before it lists its tools, so these are as Sanity's documentation names them (read 9 Nov 2026). They may be out of date.
-
dataset_assets_upload_from_web_chatgptUpload a ChatGPT web attachment or generated file to a Content Lake dataset.
-
dataset_assets_upload_from_urlStart an image or file upload from a public HTTPS URL to a Content Lake dataset.
-
media_library_upload_from_urlStart an image, video, or file upload from a public HTTPS URL to a Media Library.
-
media_assets_upload_from_urlDeprecated. Use media_library_upload_from_url with the same arguments.
-
assets_upload_statusCheck one to 20 asset uploads using operationIds.
-
media_library_upload_from_filePrepare a one-use URL to upload a local or private image, video, or file up to 50 MiB to a Media Library.
-
dataset_assets_upload_from_filePrepare a one-use URL for uploading an image or file up to 50 MiB to a Content Lake dataset.
-
get_schemaFetch the deployed schema for a project and dataset.
-
list_workspace_schemasDeprecated tool that lists every deployed schema for a project and dataset, grouped by source.
-
deploy_schemaDirectly deploy schema types to the cloud.
-
undeploy_schemaRemove a legacy MCP-managed schema from an explicitly named workspace.
-
schema_type_getRead one type from the current MCP-managed or Studio-deployed schema before calling a granular schema edit tool.
-
schema_types_deleteRemove one or more types from the dataset schema.
-
schema_fields_patchAdd, replace, or remove top-level fields on one document or object type.
-
deploy_studioDeploy a managed Sanity Studio bound to an MCP-managed schema.
-
create_documentsCreate one or more documents by directly providing structured content.
-
create_versionCreate a version document (versions.{releaseId}.* prefix) for a specific release.
-
patch_documentsUpdate existing documents with @sanity/client patch() operations.
-
query_documentsQuery documents from Sanity using GROQ.
-
generate_imageTrigger async AI image generation for a document field.
-
transform_imageTrigger async AI transformation of an existing image.
-
get_documentFetch a single document by its exact ID.
-
documents_validateValidate documents against the deployed schema without modifying them.
-
publish_documentsPublish one or more drafts.
-
unpublish_documentsUnpublish one or more published documents (moves them back to drafts)
-
discard_draftsDiscard one or more draft documents (deletes drafts while keeping published documents intact)
-
version_discardDiscard one or more document versions from a release
-
list_organizationsLists all organizations the user has access to in Sanity
-
list_projectsLists all Sanity projects associated with your account
-
get_project_studiosRetrieves all studio applications linked to a specific Sanity project
-
create_projectCreates a new Sanity project and initializes it with a dataset and API tokens
-
cors_origins_listLists all CORS origins configured for a Sanity project
-
add_cors_originAdds CORS origin(s) to allow client-side requests to a Sanity project
-
cors_origins_deleteDeletes a CORS origin from a Sanity project
-
whoamiReturns the currently authenticated Sanity account.
-
list_datasetsLists all datasets in your Sanity project
-
create_datasetCreates a new dataset with specified name and access settings
-
update_datasetUpdate an existing dataset's visibility (public or private) and description.
-
create_releaseCreate a new release for grouping content changes.
-
list_releasesList releases in a dataset.
-
list_embeddings_indicesList all available embeddings indices for a dataset
-
semantic_searchPerform a semantic search on an embeddings index
-
media_library_listLists the Sanity Media Libraries in an organization.
-
media_library_get_schemaGet the document types of a Media Library, or the full field definitions for one type.
-
media_library_query_documentsQuery a Media Library using GROQ.
-
media_library_get_documentFetch a single Media Library document by its exact ID.
-
media_library_create_documentsCreate documents in a Media Library.
-
media_library_patch_documentsEdit Media Library documents.
-
media_library_publish_documentsPublish asset drafts to make unpublished metadata edits (title, aspects.*) live.
-
media_library_discard_draftsDiscard asset drafts, throwing away unpublished metadata edits and leaving the published asset intact.
-
media_library_list_asset_referencesLists documents (across project datasets) that reference a Media Library asset.
-
media_library_link_assetsMake one or more Media Library assets usable in project documents.
-
usage_snapshot_getGet metered usage totals for a project, organization or media library over one billing period.
-
usage_history_getGet metered usage for a project, organization or media library as a series of daily, monthly or yearly data points.
-
run_sanity_cliRun a limited subset of Sanity CLI commands and return their output.
-
search_docsSearch Sanity docs
-
read_docsFetch a specific documentation article.
-
list_sanity_rulesList available best-practice development rules.
-
get_sanity_rulesLoad specific best-practice development rules.
-
give_sanity_feedbackSubmit feedback about Sanity when you encounter issues while working with a Sanity codebase or project.
Sanity
Direct access to your Sanity projects (content, datasets, releases, schemas) and agent rules
- Address
- https://mcp.sanity.io
- Runs
- Hosted
- Sign-in
- Vendor docs
- Cost to use
- Most tools use no AI credits; generate_image and transform_image consume AI creditsFrom Sanity's own page
- Official MCP Registry
-
Listed as
io.sanity.www/mcp· published 30 Sep 2026 - How we know it's official
-
- Published in the official MCP Registry as io.sanity.www/mcp, a name only the owner of sanity.io can publish under.
- Documentation
- www.sanity.io/docs/ai/mcp-server
- Source code
- github.com/sanity-io/agent-toolkit
- Tools
- 53 tools · from Sanity's documentation
- First seen
- 30 Sep 2026
- Last checked
-
Reachable ·
16 Nov 2026: reachable17 Nov 2026: reachable18 Nov 2026: reachable19 Nov 2026: reachable20 Nov 2026: reachable21 Nov 2026: reachable22 Nov 2026: reachable
- Uptime
- 100% · 55 of 55 checks reachable since 1 Oct 2026
Sanity tools (53)
The server needs sign-in before it lists its tools, so these are as Sanity's documentation names them (read 3 Oct 2026). They may be out of date.
-
dataset_assets_upload_from_web_chatgptUpload a ChatGPT web attachment or generated file to a Content Lake dataset.
-
dataset_assets_upload_from_urlStart an image or file upload from a public HTTPS URL to a Content Lake dataset.
-
media_library_upload_from_urlStart an image, video, or file upload from a public HTTPS URL to a Media Library.
-
media_assets_upload_from_urlDeprecated. Use media_library_upload_from_url with the same arguments.
-
assets_upload_statusCheck one to 20 asset uploads using operationIds.
-
dataset_assets_upload_from_filePrepare a one-use URL for uploading an image or file up to 50 MiB to a Content Lake dataset.
-
dataset_assets_uploadProvide local Sanity CLI guidance for uploading an image or file asset to a Content Lake dataset.
-
get_schemaFetch a deployed schema.
-
list_workspace_schemasList every deployed schema for a project and dataset, grouped by source (MCP-managed, Studio-deployed, or legacy).
-
deploy_schemaDirectly deploy schema types to the cloud.
-
deploy_studioDeploy a managed Sanity Studio bound to an MCP-managed schema.
-
create_documentsCreate one or more draft documents by directly providing structured content.
-
create_versionCreate a version document (versions.{releaseId}.* prefix) for a specific release.
-
patch_documentsUpdate existing documents with @sanity/client patch() operations.
-
query_documentsQuery documents from Sanity using GROQ.
-
generate_imageTrigger async AI image generation for a document field.
-
transform_imageTrigger async AI transformation of an existing image.
-
get_documentFetch a single document by its exact ID.
-
publish_documentsPublish one or more drafts.
-
unpublish_documentsUnpublish one or more published documents (moves them back to drafts)
-
discard_draftsDiscard one or more draft documents (deletes drafts while keeping published documents intact)
-
version_discardDiscard one or more document versions from a release
-
list_organizationsLists all organizations the user has access to in Sanity
-
list_projectsLists all Sanity projects associated with your account
-
get_project_studiosRetrieves all studio applications linked to a specific Sanity project
-
create_projectCreates a new Sanity project and initializes it with a dataset and API tokens
-
cors_origins_listLists all CORS origins configured for a Sanity project
-
add_cors_originAdds CORS origin(s) to allow client-side requests to a Sanity project
-
cors_origins_deleteDeletes a CORS origin from a Sanity project
-
whoamiReturns the currently authenticated Sanity account.
-
list_datasetsLists all datasets in your Sanity project
-
create_datasetCreates a new dataset with specified name and access settings
-
update_datasetModifies a dataset's name or access control settings
-
create_releaseCreate a new release for grouping content changes.
-
list_releasesList releases in a dataset.
-
list_embeddings_indicesList all available embeddings indices for a dataset
-
semantic_searchPerform a semantic search on an embeddings index
-
media_library_listLists the Sanity Media Libraries in an organization.
-
media_library_get_schemaGet the document types of a Media Library, or the full field definitions for one type.
-
media_library_query_documentsQuery a Media Library using GROQ.
-
media_library_get_documentFetch a single Media Library document by its exact ID.
-
media_library_create_documentsCreate documents in a Media Library.
-
media_library_patch_documentsEdit Media Library documents.
-
media_library_publish_documentsPublish asset drafts to make unpublished metadata edits (title, aspects.*) live, preserving published-only and system-managed fields.
-
media_library_discard_draftsDiscard asset drafts, throwing away unpublished metadata edits and leaving the published asset intact.
-
media_library_list_asset_referencesLists documents (across project datasets) that reference a Media Library asset.
-
media_library_link_assetsMake one or more Media Library assets usable in project documents.
-
run_sanity_cliRun a limited subset of Sanity CLI commands and return their output.
-
search_docsSearch Sanity docs
-
read_docsFetch a specific documentation article.
-
list_sanity_rulesList available best-practice development rules.
-
get_sanity_rulesLoad specific best-practice development rules.
-
give_sanity_feedbackSubmit feedback about Sanity when you encounter issues while working with a Sanity codebase or project.
Connect your AI to Sanity
Add the official Sanity MCP server to Claude, ChatGPT or your editor.
Connect Sanity MCP to Claude
Sanity MCP server
Claude.ai and Claude Desktop
Open Customize, then Connectors.
Click +, then Add custom connector.
Name it Sanity, paste the address below and click Add.
Sanity
Claude.ai and Claude Desktop
Open Customize, then Connectors.
Click +, then Add custom connector.
Name it Sanity, paste the address below and click Add.
Connect Sanity MCP to ChatGPT
Sanity MCP server
Open Settings, then Apps, then Advanced settings.
Turn on Developer mode, then click Create.
Name it Sanity and paste the address below.
Sanity
Open Settings, then Apps, then Advanced settings.
Turn on Developer mode, then click Create.
Name it Sanity and paste the address below.
ChatGPT usually only connects to servers with self-serve sign-in or none.
Connect Sanity MCP to Cursor
Sanity MCP server
Opens Cursor if it's installed. If nothing happens, use the JSON below.
Sanity
Opens Cursor if it's installed. If nothing happens, use the JSON below.
Connect Sanity MCP to VS Code
Sanity MCP server
Opens VS Code if it's installed. Otherwise add the JSON settings from the Cursor tab to your .vscode/mcp.json.
Sanity
Opens VS Code if it's installed. Otherwise add the JSON settings from the Cursor tab to your .vscode/mcp.json.
Sanity MCP server questions
Does Sanity have an official MCP server?
Yes. Sanity publishes 2 MCP servers itself. MartechDB only lists servers a vendor publishes, never community copies.
What is the Sanity MCP server URL?
Sanity MCP server: The address is https://mcp.sanity.io/mcp. Sanity: The address is https://mcp.sanity.io.
How do I connect Sanity MCP to Claude, ChatGPT or Cursor?
These steps are for Sanity MCP server. The others connect the same way, each at its own address. In Claude, add https://mcp.sanity.io/mcp as a custom connector (Customize, Connectors, Add custom connector). In ChatGPT, turn on developer mode (Settings, Apps, Advanced settings) and create an app with the same address. In Cursor, use the Add to Cursor link on MartechDB's page, or paste the JSON settings into your mcp.json. In Claude Code, run: claude mcp add --transport http sanity https://mcp.sanity.io/mcp
What can Sanity's MCP servers do?
Together they offer 113 tools, including dataset_assets_upload_from_web_chatgpt, dataset_assets_upload_from_url, media_library_upload_from_url, media_assets_upload_from_url and assets_upload_status (as their documentation names them, read on 9 Nov 2026).
Are Sanity's MCP servers in the official MCP Registry?
Yes, all 2 are listed there.
Are Sanity's MCP servers working?
Yes. All of them answered our most recent checks. We last checked them on 22 Nov 2026.
What are the alternatives to Sanity's MCP server?
In CMS, the most agent-friendly alternatives with an official MCP server are Webflow (95/100), Hygraph (91/100), DatoCMS (91/100), Prepr (87/100) and Optimizely (85/100). Sanity scores 85/100 on the same index.
Alternatives to Sanity's MCP server
Vendors in CMS with an official MCP server, the most agent-friendly first. Sanity scores 85/100.
Webflow
webflow.com
Hygraph
hygraph.com
DatoCMS
datocms.com
Prepr
prepr.io
Optimizely
optimizely.com
Use with AI
Connect your AI to MartechDB
Then ask it about Sanity, or any of the 1,850 marketing tools with an official MCP server. Free, no sign-in.
Claude.ai and Claude Desktop
Open Customize, then Connectors.
Click +, then Add custom connector.
Name it MartechDB, paste the address below and click Add. There's no sign-in.
The free plan allows one custom connector. On Team and Enterprise plans, an owner adds the connector first.
Claude Code
Run this in your terminal:
ChatGPT
Open Settings, then Apps, then Advanced settings.
Turn on Developer mode, then click Create.
Name it MartechDB, paste the address below and choose No authentication.
Developer mode is on Plus and Pro plans, and on Business, Enterprise and Edu if an admin allows it.
API
The same data as JSON, with no sign-in. See the OpenAPI description for every endpoint and field.
CLI
Search the directory and print the command to connect a vendor's server, from your terminal. Needs Node 18 or later. View on npm
Show that your MCP server is verified
If you work at Sanity, add this badge to your MCP docs or README. It's free, it's the same for every vendor, and it updates from our daily checks: it shows uptime while the server responds, and says so if it stops.
Something wrong or out of date? Suggest a correction or email us, and we'll check it against the evidence. Every correction we make is listed on Corrections.