AI agents use upsert_record to create or update resources in Xrm — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xrm environment.
Upsert combines create and update into a single reversible operation. It does not delete or destroy data (ruling out Destructive), does not move money (not Financial), and does not execute arbitrary code (not Execute). The sibling tools include create_record and update_record, confirming this server's Write-class operations.
From the tool's definition Tool name 'upsert_record' and server context describing 'write access to Microsoft Dataverse environments via the Dataverse Web API'. Upsert is a write operation that creates or updates records without side effects information provided in description.
Documented attack patterns abuse exactly the kind of access upsert_record gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Xrm, and nothing reaches the server without passing your rules. This is the rule we recommend for upsert_record:
{
"version": "1",
"default": "deny",
"tools": {
"upsert_record": {
"limits": [
{
"counter": "upsert_record_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}upsert_record 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_record. It is categorised as a Write tool in the Xrm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xrm MCP server in PolicyLayer and add a rule for upsert_record: 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 Xrm. Nothing to install.
upsert_record 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_record 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_record. 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_record is provided by the Xrm MCP server (jukkan/xrm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Xrm, 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.
8 Xrm tools catalogued and risk-classified — across an index of 43,000+ MCP servers.