Create new custom objects or modify existing ones in Salesforce: - Create: New custom objects with fields, relationships, and settings - Update: Modify existing object settings, labels, sharing model Examples: Create Customer_Feedback__c object, Update object sharing settings Note: Changes affect...
AI agents use salesforce_manage_object to create or update resources in Salesforce MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Salesforce MCP Server environment.
This tool creates or modifies metadata (custom objects, fields, relationships, sharing settings) but does not irreversibly delete data or invoke destructive operations. While high-impact due to schema-level changes that could affect many users and records, the operations are technically reversible (objects can be deleted, settings reverted).
From the tool's definition Tool enables 'Create' and 'Update' operations on Salesforce custom objects, explicitly stating 'Create new custom objects' and 'Modify existing object settings'. These are reversible write operations that change metadata structure.
Attacks that exploit this kind of access
Create new custom objects or modify existing ones in Salesforce: - Create: New custom objects with fields, relationships, and settings - Update: Modify existing object settings, labels, sharing model Examples: Create Customer_Feedback__c object, Update object sharing settings Note: Changes affect metadata and require proper permissions. It is categorised as a Write tool in the Salesforce MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Salesforce MCP Server MCP server in PolicyLayer and add a rule for salesforce_manage_object: 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_manage_object 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 salesforce_manage_object 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_manage_object. 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_manage_object 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 →