Update an existing Salesforce record
AI agents use update_record to create or update resources in MCP Salesforce Lite — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Salesforce Lite environment.
This tool modifies data (Salesforce records) but does not delete or destroy it, making it a Write operation rather than Destructive. The severity is medium because updates to CRM data could impact business processes, reporting, and customer relationships, but the changes are reversible through subsequent updates or restore operations.
From the tool's definition Tool name is 'update_record' and description states 'Update an existing Salesforce record', indicating modification of existing data in a reversible manner.
Attacks that exploit this kind of access
Update an existing Salesforce record. It is categorised as a Write tool in the MCP Salesforce Lite MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Salesforce Lite MCP server in PolicyLayer and add a rule for update_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 MCP Salesforce Lite. Nothing to install.
update_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 update_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 update_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.
update_record is provided by the MCP Salesforce Lite MCP server (luvl/mcp-salesforce-lite). 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 →