Execute a SOQL query on Salesforce
AI agents invoke soqlQuery to trigger actions in Salesforce MCP Integration. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
SOQL (Salesforce Object Query Language) is primarily a read/query language, but executing arbitrary queries against a live CRM system carries significant risk: queries can expose sensitive customer data, PII, financial records, or proprietary business data at scale.
From the tool's definition "Execute a SOQL query on Salesforce" — the tool runs arbitrary SOQL queries against a live Salesforce instance.
Attacks that exploit this kind of access
Execute a SOQL query on Salesforce. It is categorised as a Execute tool in the Salesforce MCP Integration MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Salesforce MCP Integration MCP server in PolicyLayer and add a rule for soqlQuery: 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 Integration. Nothing to install.
soqlQuery is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the soqlQuery 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 soqlQuery. 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.
soqlQuery is provided by the Salesforce MCP Integration MCP server (jogcruz/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 →