AI agents call metadata-retrieve 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.
The tool retrieves (reads) Salesforce metadata components without creating, modifying, deleting, or executing operations. However, severity is elevated to 'medium' because metadata retrieval can expose sensitive organizational configuration, custom field definitions, workflow rules, validation logic, and other structural details that could be leveraged for reconnaissance or further attacks if misused by an AI agent.
From the tool's definition Tool name 'metadata-retrieve' and description 'Retrieve metadata components from Salesforce' indicate a data retrieval operation with no modification or deletion.
Documented attack patterns abuse exactly the kind of access metadata-retrieve 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 metadata-retrieve:
{
"version": "1",
"default": "deny",
"tools": {
"metadata-retrieve": {}
}
}metadata-retrieve 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.
Retrieve metadata components from Salesforce. 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 metadata-retrieve: 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.
metadata-retrieve 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 metadata-retrieve 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 metadata-retrieve. 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.
metadata-retrieve 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.