Run Apex tests in a Salesforce org
AI agents invoke sf_apex_test_run 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.
Running Apex tests triggers code execution in the Salesforce org. While typically read-only in intent, test execution can have side effects depending on test implementations (DML operations, callouts, etc.), making this an Execute-category action. Misuse could consume governor limits or trigger unintended org-side effects, warranting medium severity.
From the tool's definition 'Run Apex tests in a Salesforce org' — executes test code within a live Salesforce org environment
Attacks that exploit this kind of access
Run Apex tests in a Salesforce org. 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 sf_apex_test_run: 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.
sf_apex_test_run 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 sf_apex_test_run 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 sf_apex_test_run. 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.
sf_apex_test_run is provided by the Salesforce CLI MCP Server MCP server (timaw513-emergenit/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 →