AI agents call search_records 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 and queries data without side effects. It performs a search operation across Salesforce objects, which is a non-destructive read operation. The low severity reflects that searches alone cannot modify state, execute code, or commit financial actions. Confidence is high because the function name and description are explicit about the search/retrieval nature.
From the tool's definition Tool name 'search_records' and description 'Search for Salesforce records across multiple objects' indicate a read-only query operation. No modification, deletion, or execution capability is described.
Documented attack patterns abuse exactly the kind of access search_records 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 search_records:
{
"version": "1",
"default": "deny",
"tools": {
"search_records": {}
}
}search_records 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.
Search for Salesforce records across multiple objects. 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 search_records: 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.
search_records 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 search_records 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 search_records. 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.
search_records is provided by the Salesforce MCP server (tomnagengast/mcp-server-salesforce). 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.
9 Salesforce tools catalogued and risk-classified — across an index of 43,000+ MCP servers.