sanity_query · Sanity MCP Server MCP: Risk & Policy

WHAT IT DOES

What sanity_query does on Sanity MCP Server

AI agents invoke sanity_query to trigger actions in Sanity MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why sanity_query needs a policy

The tool executes GROQ queries against a Sanity CMS. While GROQ is primarily a read/query language, executing arbitrary queries can have side effects depending on the server's implementation and GROQ extensions. Given the server description mentions 'full CRUD' and 'atomic transactions', there is a meaningful risk that GROQ queries could trigger mutations or destructive operations.

From the tool's definition "Execute a GROQ query against Sanity CMS" — explicitly executes a query language against a CMS backend

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sanity_query Rate-limited

sanity_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sanity_query": {
      "limits": [
        {
          "counter": "sanity_query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Sanity MCP Server, so you can run agents against it safely.

FAQ

Questions about sanity_query

What does the sanity_query tool do? +

Execute a GROQ query against Sanity CMS. GROQ is a query language similar to GraphQL but designed for JSON documents. Examples:. It is categorised as a Execute tool in the Sanity MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on sanity_query? +

Register the Sanity MCP Server MCP server in PolicyLayer and add a rule for sanity_query: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Sanity MCP Server. Nothing to install.

What risk level is sanity_query? +

sanity_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit sanity_query? +

Yes. Add a rate_limit block to the sanity_query rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block sanity_query completely? +

Set action: deny in the PolicyLayer policy for sanity_query. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides sanity_query? +

sanity_query is provided by the Sanity MCP Server MCP server (purple-horizons/sanity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.