Execute anonymous Apex code with debug log capture
AI agents invoke execute-apex to trigger actions in Salesforce 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 permits execution of arbitrary Apex code in a Salesforce environment. Apex is Salesforce's proprietary server-side programming language with full access to org data, APIs, and configuration. An AI agent with this tool could execute malicious code to steal data, modify records, disable security controls, or compromise the entire Salesforce org.
From the tool's definition Tool name is 'execute-apex' and description states 'Execute anonymous Apex code with debug log capture'. The verb 'Execute' combined with 'anonymous Apex code' indicates arbitrary code execution capability.
Documented attack patterns abuse exactly the kind of access execute-apex gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Salesforce MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute-apex:
{
"version": "1",
"default": "deny",
"tools": {
"execute-apex": {
"limits": [
{
"counter": "execute-apex_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute-apex stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute anonymous Apex code with debug log capture. It is categorised as a Execute tool in the Salesforce MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Salesforce MCP Server MCP server in PolicyLayer and add a rule for execute-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 MCP Server. Nothing to install.
execute-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-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-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-apex is provided by the Salesforce MCP Server MCP server (jaworjar95/salesforce-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Salesforce MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 Salesforce MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.