Execute a SOQL query (SELECT only). Returns query results including records, totalSize, and done.
AI agents call run_soql 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 explicitly restricts to SELECT-only SOQL queries, meaning it retrieves data without modifying it. The server description also confirms 'read-only access to Salesforce orgs'. Severity is medium because SOQL queries can expose sensitive CRM data (customer records, financial data, contacts) at scale if misused.
From the tool's definition Execute a SOQL query (SELECT only). Returns query results including records, totalSize, and done.
Attacks that exploit this kind of access
Execute a SOQL query (SELECT only). Returns query results including records, totalSize, and done. 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 run_soql: 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.
run_soql 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 run_soql 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 run_soql. 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.
run_soql is provided by the Salesforce MCP server (pmankar-netchex/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 →