query_salesforce · MCP Salesforce Revenue Cloud MCP

WHAT IT DOES

What query_salesforce does on MCP Salesforce Revenue Cloud

AI agents invoke query_salesforce to trigger actions in MCP Salesforce Revenue Cloud. 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 query_salesforce needs a policy

The server description explicitly states it enables 'execution of custom SOQL queries through natural language,' and this tool is the most likely candidate for that functionality given its generic 'query' name versus the other sibling tools which are specific read operations.

From the tool's definition Tool name 'query_salesforce' on a server that explicitly mentions 'execution of custom SOQL queries' as a capability. Description is empty, lowering confidence.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_salesforce Rate-limited

query_salesforce 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": {
    "query_salesforce": {
      "limits": [
        {
          "counter": "query_salesforce_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 MCP Salesforce Revenue Cloud, so you can run agents against it safely.

FAQ

Questions about query_salesforce

What does the query_salesforce tool do? +

query_salesforce. It is categorised as a Execute tool in the MCP Salesforce Revenue Cloud MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_salesforce? +

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

What risk level is query_salesforce? +

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

Can I rate-limit query_salesforce? +

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

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

query_salesforce is provided by the MCP Salesforce Revenue Cloud MCP server (marijanmiletic/mcp_salesforce_revenue_cloud). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.