🧠LLM-POWERED: Expand a natural language query into optimal search keywords. Use this FIRST when a user asks a vibe-style question that doesn
AI agents call expand_search_query to retrieve information from Salesforce Documentation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure read operation that performs query expansion/transformation to improve downstream search effectiveness. It retrieves no data itself, modifies nothing, and has no side effects—it simply enhances natural language into searchable keywords.
From the tool's definition The tool description states it 'Expand[s] a natural language query into optimal search keywords' and is positioned as a preprocessing step ('Use this FIRST') before actual searches.
Documented attack patterns abuse exactly the kind of access expand_search_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Salesforce Documentation MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for expand_search_query:
{
"version": "1",
"default": "deny",
"tools": {
"expand_search_query": {}
}
} expand_search_query 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.
🧠LLM-POWERED: Expand a natural language query into optimal search keywords. Use this FIRST when a user asks a vibe-style question that doesn. It is categorised as a Read tool in the Salesforce Documentation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Salesforce Documentation MCP Server MCP server in PolicyLayer and add a rule for expand_search_query: 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 Documentation MCP Server. Nothing to install.
expand_search_query 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 expand_search_query 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 expand_search_query. 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.
expand_search_query is provided by the Salesforce Documentation MCP Server MCP server (salesforcediariesbysanket/salesforce-docs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Salesforce Documentation MCP Server, 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.
9 Salesforce Documentation MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.