Get an entity by kind and key from Datastore
AI agents call datastore_get 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.
The tool retrieves a single entity from a Datastore by specifying its kind and key. This is a read-only operation with no side effects—it does not create, modify, delete, or execute code. Even in a broader context where the server includes destructive operations (datastore_delete) and write operations (datastore_insert, datastore_update, datastore_upsert), this specific tool is purely a data query.
From the tool's definition Tool name 'datastore_get' and description 'Get an entity by kind and key from Datastore' indicate retrieval of data without modification or deletion.
Attacks that exploit this kind of access
Get an entity by kind and key from Datastore. 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_get: 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_get 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_get 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_get. 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_get is provided by the MCP Datastore Server MCP server (petekmet/mcp-gcp-datastore). 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 →