apex_execute · Salesforce MCP: Risk & Policy

WHAT IT DOES

What apex_execute does on Salesforce

AI agents invoke apex_execute to trigger actions in Salesforce. 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.

WHY IT NEEDS A POLICY

Why apex_execute needs a policy

This tool executes code (Apex) in a live Salesforce environment. Although the sister tool 'tooling_execute' might suggest Execute category, 'apex_execute' explicitly runs REST requests in Apex, which is code execution. The blast radius is high because Apex execution can trigger business logic, modify data, call external APIs, and produce side effects beyond the caller's control.

From the tool's definition Tool name and description indicate execution of Apex REST requests. Apex is Salesforce's proprietary programming language; executing arbitrary Apex code allows arbitrary logic to run within the Salesforce environment, with effects dependent on the code…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

apex_execute Rate-limited

apex_execute 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "apex_execute": {
      "limits": [
        {
          "counter": "apex_execute_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Salesforce, so you can run agents against it safely.

FAQ

Questions about apex_execute

What does the apex_execute tool do? +

Executes an Apex REST request. It is categorised as a Execute tool in the Salesforce MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on apex_execute? +

Register the Salesforce MCP server in PolicyLayer and add a rule for apex_execute: 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. Nothing to install.

What risk level is apex_execute? +

apex_execute is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit apex_execute? +

Yes. Add a rate_limit block to the apex_execute 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.

How do I block apex_execute completely? +

Set action: deny in the PolicyLayer policy for apex_execute. 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.

What MCP server provides apex_execute? +

apex_execute is provided by the Salesforce MCP server (leilaabdel/mcp-salesforce). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.