execute_tooling_query

THE RISK

High Risk

Why execute_tooling_query needs a policy

This tool triggers external operations (database queries against Salesforce Tooling API) whose effects depend entirely on the SOQL query provided as an argument. While SOQL queries alone may be read-only, the classification must account for the fact that arbitrary SOQL execution against metadata systems can be chained with destructive operations and represents a significant risk vector if an AI agent constructs…

From the tool's definition Tool name contains 'execute' and description states 'Execute SOQL queries against Tooling API'. SOQL queries can be arbitrary and potentially destructive (e.g., querying then deleting metadata).

Documented attack patterns abuse exactly the kind of access execute_tooling_query gives an agent:

POLICY

How to control execute_tooling_query

PolicyLayer is an MCP gateway — it sits between your AI agents and Salesforce, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_tooling_query:

policy.json

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

execute_tooling_query 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.

Create a free account and register Salesforce — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Salesforce tools

Destructive delete_apex_class Delete an Apex class (use with caution) Execute call_rest_api Make a generic REST API call to Salesforce (supports GET, POST, PATCH, DELETE) Execute run_tests Execute Apex tests Write create_apex_class Create a new Apex class Write update_apex_class Update the source code of an existing Apex class Read analyze_soql_performance Analyze SOQL query performance Read check_apex_sharing Check Apex class sharing declarations Read describe_sobject Describe a specific SObject using REST API

All 25 Salesforce tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Salesforce → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about execute_tooling_query

What does the execute_tooling_query tool do? +

Execute SOQL queries against Tooling API. 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 execute_tooling_query? +

Register the Salesforce MCP server in PolicyLayer and add a rule for execute_tooling_query: 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 execute_tooling_query? +

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

Can I rate-limit execute_tooling_query? +

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

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

execute_tooling_query is provided by the Salesforce MCP server (ryu-727/salesforce-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Salesforce tool call.

Start from Salesforce, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →