Perform data manipulation operations on Salesforce records: - insert: Create new records - update: Modify existing records (requires Id) - delete: Remove records (requires Id) - upsert: Insert or update based on external ID field Examples: Insert new Accounts, Update Case status, Delete old recor...
AI agents call salesforce_dml_records to permanently remove resources in Salesforce MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the tool also supports insert, update, and upsert operations (which would normally be classified as Write), the presence of the delete capability elevates this to Destructive. Delete operations are irreversible and cannot be undone—they permanently remove data. When a tool spans multiple categories, the most severe (Destructive > Write) takes precedence.
From the tool's definition The tool description explicitly includes 'delete: Remove records (requires Id)' as one of its core DML operations. It performs irreversible deletion of Salesforce records.
Attacks that exploit this kind of access
Perform data manipulation operations on Salesforce records: - insert: Create new records - update: Modify existing records (requires Id) - delete: Remove records (requires Id) - upsert: Insert or update based on external ID field Examples: Insert new Accounts, Update Case status, Delete old records, Upsert based on custom external ID. It is categorised as a Destructive tool in the Salesforce MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Salesforce MCP Server MCP server in PolicyLayer and add a rule for salesforce_dml_records: 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 MCP Server. Nothing to install.
salesforce_dml_records is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the salesforce_dml_records 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 salesforce_dml_records. 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.
salesforce_dml_records is provided by the Salesforce MCP Server MCP server (jeresalguero30/mcp-server-salesforce). 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 →