Update records
AI agents use update-records to create or update resources in Salesforce MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Salesforce MCP environment.
This tool modifies data reversibly by updating existing Salesforce records. It does not delete data (which would be Destructive) or move money (Financial). While it can cause significant business impact if misused (e.g., updating critical customer or financial records), the change is theoretically reversible through subsequent updates or audit logs.
From the tool's definition Tool name 'update-records' and description 'Update records' indicate modification of existing data in Salesforce. The tool is part of a Salesforce data management suite with permissions to interact with the Salesforce API.
Attacks that exploit this kind of access
Update records. It is categorised as a Write tool in the Salesforce MCP 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-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. Nothing to install.
update-records 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-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 update-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.
update-records is provided by the Salesforce MCP server (jpmonette/salesforce-mcp). 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 →