Search Salesforce records
AI agents call query-records to retrieve information from Salesforce MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a search/query operation to retrieve Salesforce records, which is a read-only action with no side effects on data. Severity is medium rather than low because Salesforce often contains sensitive business and customer data; unauthorized access via a compromised AI agent could expose PII, financial records, or proprietary information, though the tool itself does not modify or delete data.
From the tool's definition Tool name 'query-records' and description 'Search Salesforce records' indicate a read operation that retrieves data without modifying it.
Attacks that exploit this kind of access
Search Salesforce records. It is categorised as a Read tool in the Salesforce MCP MCP Server, which means it retrieves data without modifying state.
Register the Salesforce MCP server in PolicyLayer and add a rule for query-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 MCP. Nothing to install.
query-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 query-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 query-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.
query-records is provided by the Salesforce MCP server (jpmonette/salesforce-mcp). 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 →