// SCAN REPORT

Sanity

36 tools. 24 can modify or destroy data without limits.

7 destructive tools with no built-in limits. Policy required.

Last updated: 5 Apr 2026

24 can modify or destroy data

12 read-only

36 tools total

// TOOL MAP

Read (12) Write / Execute (17) Destructive / Financial (7)

// WHAT CAN GO WRONG

Destructive tools (delete_document, delete_release, discard_version) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (archive_release, create_dataset, create_document) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (transform_document) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and Sanity. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @@sanity/mcp-server

Scans every tool. Generates a policy. Starts enforcing.

Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client

// RECOMMENDED RULES

Deny destructive operations

delete_document:
  rules:
    - action: deny

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

archive_release:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

get_groq_specification:
  rules:
    - rate_limit: 60/minute

Controls API costs and prevents retry loops from exhausting upstream rate limits.

// ALL 36 SANITY TOOLS

DESTRUCTIVE 7 tools

Destructive delete_document Destructive delete_release Destructive discard_version Destructive unpublish_document Destructive unschedule_release Destructive version_discard_document Destructive version_unpublish_document

EXECUTE 1 tools

Execute transform_document

WRITE 16 tools

Write archive_release Write create_dataset Write create_document Write create_release Write create_version Write edit_release Write mark_for_unpublish Write patch_document Write publish_document Write publish_release Write schedule_release Write translate_document Write unarchive_release Write update_dataset Write update_document Write version_replace_document

READ 12 tools

Read get_groq_specification Read get_initial_context Read get_project_studios Read get_sanity_config Read get_schema Read list_datasets Read list_embeddings_indices Read list_projects Read list_releases Read list_workspace_schemas Read query_documents Read semantic_search

// FAQ

Can an AI agent delete data through the Sanity MCP server? +

Yes. The Sanity server exposes 7 destructive tools including delete_document, delete_release, discard_version. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Sanity? +

The Sanity server has 16 write tools including archive_release, create_dataset, create_document. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the Sanity MCP server expose? +

36 tools across 4 categories: Destructive, Execute, Read, Write. 12 are read-only. 24 can modify, create, or delete data.

How do I add Intercept to my Sanity setup? +

One line change. Instead of running the Sanity server directly, prefix it with Intercept: intercept -c sanity.yaml -- npx -y @@@sanity/mcp-server. Download a pre-built policy from policylayer.com/policies/sanity and adjust the limits to match your use case.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init

Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.

Sanity

One command. Full control.

Other MCP servers with similar tools.

Control every MCP tool call your agent makes.

Control every MCP tool call
your agent makes.