Count entities in a kind, optionally with a filter
AI agents call datastore_count to retrieve information from MCP Datastore Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and counts existing data in Google Cloud Datastore. It has no side effects—it does not create, modify, delete, or execute arbitrary code. The confidence is high because counting is inherently a read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool performs a count operation on entities 'optionally with a filter', which retrieves aggregate data without modifying or deleting anything. The server description emphasizes 'query capabilities' and 'count entities' as read-only operations.
Attacks that exploit this kind of access
Count entities in a kind, optionally with a filter. It is categorised as a Read tool in the MCP Datastore Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Datastore Server MCP server in PolicyLayer and add a rule for datastore_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 MCP Datastore Server. Nothing to install.
datastore_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 datastore_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 datastore_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.
datastore_count is provided by the MCP Datastore Server MCP server (johnreitano/daisy). 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 →