sf_create_sandbox
Creates a new sandbox org via the Tooling API (SandboxInfo object). Supports Developer, Developer Pro, Partial Copy, and Full sandbox types. Optionally specify an Apex class to run after the sandbox copy completes. The sandbox creation is asynchronous — use sf_list_sandboxes to monitor the status.
This record as markdown: /tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-create-sandbox.md
What sf_create_sandbox does on Salesforce Metadata Mcp
AI agents use sf_create_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.
Why sf_create_sandbox is rated Medium
This tool creates a new sandbox environment in Salesforce, which is a reversible action that modifies the organizational structure. While sandbox creation is not destructive (sandboxes can be deleted), it provisionally allocates resources and creates new isolated environments. This is a Write-class action because it creates and establishes new infrastructure.
From the tool's definition Creates a new sandbox org via the Tooling API (SandboxInfo object). Supports Developer, Developer Pro, Partial Copy, and Full sandbox types.
Attacks that exploit this kind of access
The rule that runs sf_create_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_create_sandbox, this is the rule to start with:
sf_create_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Salesforce Metadata Mcp, apply this rule, and every sf_create_sandbox call is checked against it from then on.
Questions about sf_create_sandbox
Creates a new sandbox org via the Tooling API (SandboxInfo object). Supports Developer, Developer Pro, Partial Copy, and Full sandbox types. Optionally specify an Apex class to run after the sandbox copy completes. The sandbox creation is asynchronous — use sf_list_sandboxes to monitor the 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.
Register the Salesforce Metadata MCP server in PolicyLayer and add a rule for sf_create_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.
sf_create_sandbox is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the sf_create_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.
Set action: deny in the PolicyLayer policy for sf_create_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.
sf_create_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.
More on Salesforce Metadata, and thousands of servers like it.
This server
Across the catalogue