salesforce_query_records · Salesforce MCP: Risk & Policy

WHAT IT DOES

What salesforce_query_records does on Salesforce

AI agents invoke salesforce_query_records 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 salesforce_query_records needs a policy

While SOQL is primarily a read/query language, executing arbitrary queries against a multi-tenant Salesforce CRM exposes potentially sensitive customer, financial, and operational data at scale. The tool 'executes' queries rather than simply retrieving pre-defined data, and the blast radius of an AI agent issuing malformed or malicious queries (e.g., exfiltrating all contact/opportunity records) is high.

From the tool's definition "Execute a SOQL query against Salesforce" — the tool runs arbitrary SOQL queries against a live CRM system, with support for relationship traversal and complex query patterns.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

salesforce_query_records Rate-limited

salesforce_query_records 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": {
    "salesforce_query_records": {
      "limits": [
        {
          "counter": "salesforce_query_records_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 salesforce_query_records

What does the salesforce_query_records tool do? +

Execute a SOQL query against Salesforce. Supports parent-to-child and child-to-parent relationship queries. For aggregate queries (GROUP BY, COUNT, SUM), use salesforce_aggregate_query instead. 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 salesforce_query_records? +

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

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

Can I rate-limit salesforce_query_records? +

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

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

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