Execute a raw SOQL query against a Salesforce Org from a project. This command allows you to execute any SOQL query with complete control over the query structure. The query is executed using the Data Cloud API and results are returned in JSON format. Use this for complex queries, subqueries, agg...
AI agents invoke execute_soql_query to trigger actions in Salesforce CLI MCP Server. 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.
This tool executes arbitrary SOQL queries against a live Salesforce organization. While SOQL itself is read-only by design and cannot perform destructive operations (DELETE/UPDATE require DML), the tool permits complete control over query structure and can extract sensitive data at scale, trigger side effects through formula fields or workflow evaluations, and combined with the server's other capabilities…
From the tool's definition 'Execute any SOQL query with complete control over the query structure' and 'The query is executed exactly as provided' indicates arbitrary query execution capability.
Attacks that exploit this kind of access
Execute a raw SOQL query against a Salesforce Org from a project. This command allows you to execute any SOQL query with complete control over the query structure. The query is executed using the Data Cloud API and results are returned in JSON format. Use this for complex queries, subqueries, aggregations, or any SOQL that cannot be constructed with the structured query_records tool. The query will be executed exactly as provided, so ensure proper SOQL syntax. It is categorised as a Execute tool in the Salesforce CLI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Salesforce CLI MCP Server MCP server in PolicyLayer and add a rule for execute_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 CLI MCP Server. Nothing to install.
execute_soql_query 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 execute_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 execute_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.
execute_soql_query is provided by the Salesforce CLI MCP Server MCP server (perrynet/salesforce-cli-mcp-server). 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 →