AI agents invoke tooling-query 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.
The Salesforce Tooling API is a specialized API designed for developer tooling that goes beyond standard data retrieval — it can interact with Apex code, triggers, and metadata in ways that can have side effects. While a basic query is a Read operation, the Tooling API specifically enables execution-style interactions (e.g., running anonymous Apex, modifying code coverage, interacting with debug logs).
From the tool's definition "Execute a query against the Salesforce Tooling API" — the Tooling API is not a simple read interface; it allows execution of SOQL/SOSL queries against metadata and code artifacts, and can potentially trigger operations beyond simple reads
Documented attack patterns abuse exactly the kind of access tooling-query gives an agent:
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 tooling-query:
{
"version": "1",
"default": "deny",
"tools": {
"tooling-query": {
"limits": [
{
"counter": "tooling-query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
Execute a query against the Salesforce 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.
Register the Salesforce MCP server in PolicyLayer and add a rule for 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.
tooling-query 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 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.
Set action: deny in the PolicyLayer policy for 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.
tooling-query is provided by the Salesforce MCP server (kablewy/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, 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.
4 Salesforce tools catalogued and risk-classified — across an index of 43,000+ MCP servers.