deploy-schema

A command workflow for publishing a Sanity content schema—the definition of the document types and fields used by a Sanity project—to Sanity's online Content Lake.

In plain words
What is it for?
Use it after adding or changing document types, fields, or validation rules, especially before using Sanity content tools that depend on the updated schema.
Why use it?
It checks the schema before publishing, warns about possible breaking changes, and verifies that the new types and fields are available afterward.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/sanity-io/agent-toolkit/deploy-schema
Clone the repo
git clone --depth 1 https://github.com/sanity-io/agent-toolkit
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 337 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00337
Opus 5 $0.00007 $0.00169
Sonnet 5 $0.00003 $0.00067
Haiku 4.5 $0.00001 $0.00034

Measured yesterday against content hash 242db995c077, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploy-schema scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/deploy-schema.md · 60 lines

What it actually says

Deploy Sanity Schema

I'll help you deploy your schema to the Sanity Content Lake.

Why Deploy Schema?

Schema deployment is required for:

  • ⚠️ MCP Server content operations (create_documents, patch_documents) to use the latest schema
  • Embedded Studios
  • Scheduled Publishing
  • Cloud Functions with schema validation

Deployment Command

npx sanity schemas deploy

What I'll Do

  1. Pre-Deploy Check

    • Verify schema syntax (run typegen)
    • Check for breaking changes
    • Warn about removed fields with data
  2. Deploy

    • Run npx sanity schemas deploy
    • Confirm success
  3. Post-Deploy Verification

    • Use MCP get_schema to verify deployment
    • Confirm new types/fields are available

When to Deploy

Scenario Deploy?
Added new document type ✅ Yes
Added/modified fields ✅ Yes
Changed validation rules ✅ Yes
Using MCP content tools after schema changes ✅ Yes
Local dev only (no MCP) Optional

Important Notes

  • Schema deployment is fast (~2 seconds)
  • Does NOT deploy the Studio app (use npx sanity deploy for that)
  • Always deploy before MCP content operations after schema changes

Usage

"Deploy my schema" "Check if my schema is deployed" "Why can't MCP see my new field?"

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 60 lines · 14 tokens per session scan A 242db995c077

Subscribe to this mod's changes

deploy-schema is a command published in the GitHub repository sanity-io/agent-toolkit (180 stars, last pushed 6d ago), licensed MIT. It adds 14 tokens to every session and 337 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.