Executes a SOQL query against Salesforce
AI agents call run_soql_query 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.
SOQL is a SELECT-only query language; it cannot modify or delete data. However, severity is medium because queries could expose sensitive CRM data (contacts, financials, PII) at scale if misused. Confidence is slightly below 1.0 because the description doesn't explicitly restrict to SELECT statements, and the tool name says 'execute', but SOQL by definition is read-only.
From the tool's definition 'Executes a SOQL query against Salesforce' — SOQL (Salesforce Object Query Language) is a read-only query language used to retrieve data from Salesforce objects.
Attacks that exploit this kind of access
Executes a SOQL query against 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 run_soql_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. Nothing to install.
run_soql_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 run_soql_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 run_soql_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.
run_soql_query is provided by the Salesforce MCP server (leilaabdel/mcp-salesforce). 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 →