Execute Apex code in a Salesforce Org from a project. This command allows you to run Apex code directly against a specified Salesforce Org. The code is executed in the context of the Org, and the results are returned in JSON format. You can use this command to test Apex code snippets, run batch j...
AI agents invoke execute_anonymous_apex 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 Apex code in a live Salesforce organization, making it Execute category. Severity is critical because: (1) Apex runs in the org's context with full access to org data and operations, (2) an AI agent could execute destructive queries, data modifications, or financial transactions depending on the Apex code, (3) the blast radius includes the entire Salesforce org and its data.
From the tool's definition 'Execute Apex code in a Salesforce Org' and 'run Apex code directly against a specified Salesforce Org' indicate arbitrary code execution.
Attacks that exploit this kind of access
Execute Apex code in a Salesforce Org from a project. This command allows you to run Apex code directly against a specified Salesforce Org. The code is executed in the context of the Org, and the results are returned in JSON format. You can use this command to test Apex code snippets, run batch jobs, or perform other Apex-related tasks. You can review the debug logs of the execution to see the results of the code execution. 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_anonymous_apex: 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_anonymous_apex 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_anonymous_apex 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_anonymous_apex. 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_anonymous_apex 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 →