Get a specific Salesforce record.
AI agents call salesforce_get_record to retrieve information from WWIDE MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a single Salesforce record by identifier. It performs a read-only query operation with no capability to create, modify, delete, or execute code. The blast radius of misuse is minimal—at worst, an AI agent could access sensitive customer or business data already stored in Salesforce, but cannot alter systems or trigger financial transactions.
From the tool's definition Tool name 'salesforce_get_record' and description 'Get a specific Salesforce record' indicate retrieval of existing data with no modifications or side effects.
Attacks that exploit this kind of access
Get a specific Salesforce record. It is categorised as a Read tool in the WWIDE MCP Server MCP Server, which means it retrieves data without modifying state.
Register the WWIDE MCP Server MCP server in PolicyLayer and add a rule for salesforce_get_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 WWIDE MCP Server. Nothing to install.
salesforce_get_record is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the salesforce_get_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 salesforce_get_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.
salesforce_get_record is provided by the WWIDE MCP Server MCP server (kulvir88/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 →