sf_custom_command · Salesforce CLI MCP Server MCP

WHAT IT DOES

What sf_custom_command does on Salesforce CLI MCP Server

AI agents invoke sf_custom_command 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.

WHY IT NEEDS A POLICY

Why sf_custom_command needs a policy

This tool permits execution of arbitrary Salesforce CLI commands without apparent constraints. An AI agent could use it to execute destructive commands (delete orgs, purge data), extract sensitive metadata, modify deployments, or trigger financial operations. The 'custom' qualifier is the key risk indicator — it bypasses the safety constraints of purpose-built sibling tools.

From the tool's definition Tool description states 'Execute a custom Salesforce CLI command' — the word 'Execute' combined with 'custom' indicates arbitrary command execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sf_custom_command Rate-limited

sf_custom_command 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": {
    "sf_custom_command": {
      "limits": [
        {
          "counter": "sf_custom_command_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 CLI MCP Server, so you can run agents against it safely.

FAQ

Questions about sf_custom_command

What does the sf_custom_command tool do? +

Execute a custom Salesforce CLI command. 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.

How do I enforce a policy on sf_custom_command? +

Register the Salesforce CLI MCP Server MCP server in PolicyLayer and add a rule for sf_custom_command: 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.

What risk level is sf_custom_command? +

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

Can I rate-limit sf_custom_command? +

Yes. Add a rate_limit block to the sf_custom_command 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 sf_custom_command completely? +

Set action: deny in the PolicyLayer policy for sf_custom_command. 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 sf_custom_command? +

sf_custom_command 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.