tooling_execute · Salesforce MCP: Risk & Policy

WHAT IT DOES

What tooling_execute does on Salesforce

AI agents invoke tooling_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 tooling_execute needs a policy

This tool executes API requests without specifying constraints on what those requests can do. The Tooling API is powerful and can trigger deployments, execute code, modify metadata, or perform other side-effectful operations.

From the tool's definition Tool name 'tooling_execute' and description 'Executes a Tooling API request' indicate execution of arbitrary API operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tooling_execute Rate-limited

tooling_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": {
    "tooling_execute": {
      "limits": [
        {
          "counter": "tooling_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 tooling_execute

What does the tooling_execute tool do? +

Executes a Tooling API 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 tooling_execute? +

Register the Salesforce MCP server in PolicyLayer and add a rule for tooling_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 tooling_execute? +

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

Can I rate-limit tooling_execute? +

Yes. Add a rate_limit block to the tooling_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 tooling_execute completely? +

Set action: deny in the PolicyLayer policy for tooling_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 tooling_execute? +

tooling_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.