Insert or update an entity in Datastore (upsert operation)
AI agents use datastore_upsert to create or update resources in MCP Datastore Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Datastore Server environment.
Upsert is a Write operation because it creates or modifies data but does not permanently delete or destroy it. The blast radius is high because an AI agent could modify critical business data, but the operation is reversible through subsequent write operations, preventing it from being classified as Destructive. Financial is not applicable as no money movement is involved.
From the tool's definition Tool description states 'Insert or update an entity in Datastore (upsert operation)'. Upsert creates new data or modifies existing data reversibly.
Attacks that exploit this kind of access
Insert or update an entity in Datastore (upsert operation). It is categorised as a Write tool in the MCP Datastore Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Datastore Server MCP server in PolicyLayer and add a rule for datastore_upsert: 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_upsert is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the datastore_upsert 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_upsert. 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_upsert 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 →