Describe an SObject and return field information
AI agents call salesforce_describe to retrieve information from Salesforce 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 and returns schema metadata about Salesforce objects. It is a non-destructive information lookup that inspects object structure and field definitions without creating, modifying, or deleting any data. Misuse would be limited to unauthorized information disclosure rather than data loss or corruption.
From the tool's definition The tool 'salesforce_describe' returns field information about an SObject. The description uses the word 'return', which indicates data retrieval with no modification.
Attacks that exploit this kind of access
Describe an SObject and return field information. It is categorised as a Read tool in the Salesforce MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Salesforce MCP Server MCP server in PolicyLayer and add a rule for salesforce_describe: 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_describe 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_describe 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_describe. 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_describe is provided by the Salesforce MCP Server MCP server (mattmahowald/sfmcp). 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 →