sf_refresh_sandbox

SERVERSalesforce Metadata Mcp SOURCEsalesforce-metadata-mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-refresh-sandbox.md

WHAT IT DOES

What sf_refresh_sandbox does on Salesforce Metadata Mcp

AI agents use sf_refresh_sandbox to create or update resources in Salesforce Metadata Mcp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Salesforce Metadata Mcp environment.

RISK

Why sf_refresh_sandbox is rated Medium

An AI agent can call sf_refresh_sandbox faster than any human can review: one bad instruction and it creates or modifies resources in Salesforce Metadata Mcp by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs sf_refresh_sandbox safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Salesforce Metadata Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For sf_refresh_sandbox, this is the rule to start with:

sf_refresh_sandbox Rate-limited

sf_refresh_sandbox stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sf_refresh_sandbox": {
      "limits": [
        {
          "counter": "sf_refresh_sandbox_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Salesforce Metadata Mcp, apply this rule, and every sf_refresh_sandbox call is checked against it from then on.

FAQ

Questions about sf_refresh_sandbox

What does the sf_refresh_sandbox tool do? +

Refreshes an existing sandbox org by re-copying it from production via the Tooling API. The sandbox must already exist (use sf_create_sandbox for new sandboxes). Refreshing resets the sandbox to the current state of the production org. The refresh is asynchronous — use sf_list_sandboxes to monitor status. It is categorised as a Write tool in the Salesforce Metadata Mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on sf_refresh_sandbox? +

Register the Salesforce Metadata MCP server in PolicyLayer and add a rule for sf_refresh_sandbox: 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 Metadata Mcp. Nothing to install.

What risk level is sf_refresh_sandbox? +

sf_refresh_sandbox is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit sf_refresh_sandbox? +

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

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

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

KEEP EXPLORING

More on Salesforce Metadata, and thousands of servers like it.

This server

All 213 Salesforce Metadata tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →