AI agents use update_apex_class to create or update resources in Salesforce — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Salesforce environment.
This tool creates or modifies data reversibly by updating Apex class source code. While the modification is code-based and could have significant runtime consequences if misused, the operation itself is reversible (prior versions can be restored, code can be reverted). It does not irreversibly delete data (which would be Destructive) nor does it execute code in production (which would be Execute).
From the tool's definition Tool description states 'Update the source code of an existing Apex class' — a write operation that modifies existing code in Salesforce.
Documented attack patterns abuse exactly the kind of access update_apex_class gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Salesforce, and nothing reaches the server without passing your rules. This is the rule we recommend for update_apex_class:
{
"version": "1",
"default": "deny",
"tools": {
"update_apex_class": {
"limits": [
{
"counter": "update_apex_class_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_apex_class 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.
Update the source code of an existing Apex class. It is categorised as a Write tool in the Salesforce MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Salesforce MCP server in PolicyLayer and add a rule for update_apex_class: 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 Salesforce. Nothing to install.
update_apex_class 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 update_apex_class 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 update_apex_class. 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.
update_apex_class is provided by the Salesforce MCP server (ryu-727/salesforce-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Salesforce, 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.
25 Salesforce tools catalogued and risk-classified — across an index of 43,000+ MCP servers.