AI agents use upsert to create or update resources in Surreal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Surreal environment.
Upsert is a standard database operation that inserts a record if it doesn't exist or updates it if it does. This is a reversible write operation (data can be modified again or deleted), not destructive. While the description is empty, the tool name and context (SurrealDB data manipulation server with similar write tools like insert, update, create) make the category clear.
From the tool's definition Tool named 'upsert' on a SurrealDB MCP server alongside create, insert, update, delete operations. Upsert (update or insert) is a write operation that creates or modifies data reversibly.
Documented attack patterns abuse exactly the kind of access upsert gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Surreal, and nothing reaches the server without passing your rules. This is the rule we recommend for upsert:
{
"version": "1",
"default": "deny",
"tools": {
"upsert": {
"limits": [
{
"counter": "upsert_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}upsert stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
upsert. It is categorised as a Write tool in the Surreal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Surreal MCP server in PolicyLayer and add a rule for 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 Surreal. Nothing to install.
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 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 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.
upsert is provided by the Surreal MCP server (lfnovo/surreal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Surreal, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 Surreal tools catalogued and risk-classified — across an index of 43,000+ MCP servers.