Count documents matching a GROQ filter
AI agents call sanity_count to retrieve information from Sanity MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation—counting documents based on a filter query. It retrieves information (a count) without creating, modifying, deleting, or executing side effects. The GROQ filter is used for querying only, not for data manipulation. This is a standard Read operation with minimal blast radius if misused (worst case: information disclosure about document counts).
From the tool's definition Tool name 'sanity_count' and description 'Count documents matching a GROQ filter' indicate a query operation that retrieves aggregated metadata without modifying data.
Attacks that exploit this kind of access
Count documents matching a GROQ filter. It is categorised as a Read tool in the Sanity MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sanity MCP Server MCP server in PolicyLayer and add a rule for sanity_count: 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.
sanity_count is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the sanity_count 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.
Set action: deny in the PolicyLayer policy for sanity_count. 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.
sanity_count 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →