AI agents call describe-object to retrieve information from Salesforce without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata information about Salesforce objects without creating, modifying, deleting, or executing any operations. It is a passive data retrieval action that does not alter system state or trigger external operations. The blast radius of misuse is limited to potential information disclosure; an agent could learn about object structure but cannot perform destructive or financial actions.
From the tool's definition Tool description states 'Get detailed metadata about a Salesforce object' — a retrieval operation with no modification or side effects. The verb 'describe' and 'get metadata' indicate read-only querying.
Documented attack patterns abuse exactly the kind of access describe-object gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Salesforce, and nothing reaches the server without passing your rules. This is the rule we recommend for describe-object:
{
"version": "1",
"default": "deny",
"tools": {
"describe-object": {}
}
}describe-object is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get detailed metadata about a Salesforce object. It is categorised as a Read tool in the Salesforce MCP Server, which means it retrieves data without modifying state.
Register the Salesforce MCP server in PolicyLayer and add a rule for describe-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. Nothing to install.
describe-object 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 describe-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 describe-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.
describe-object is provided by the Salesforce MCP server (kablewy/salesforce-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Salesforce, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Salesforce tools catalogued and risk-classified — across an index of 43,000+ MCP servers.