sf_create_apex_class
Creates and deploys an Apex class to the Salesforce org using the Metadata API. Accepts the full Apex source code including the class declaration. Use for any type of Apex class: service classes, controllers, batch classes, schedulable classes, queueable classes, test utilities, etc. IMPORTANT — ...
This record as markdown: /tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-create-apex-class.md
What sf_create_apex_class does on Salesforce Metadata Mcp
AI agents invoke sf_create_apex_class to trigger actions in Salesforce Metadata Mcp. 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 sf_create_apex_class is rated High
This tool deploys arbitrary Apex code to a live Salesforce org. Deploying code is an Execute-category action because it runs/installs executable logic with effects that depend entirely on the code provided. The blast radius is high since malicious or erroneous Apex can access, modify, or delete org data, call external services, escalate permissions, or destabilize the org.
From the tool's definition Creates and deploys an Apex class to the Salesforce org using the Metadata API. Accepts the full Apex source code including the class declaration.
Attacks that exploit this kind of access
The rule that runs sf_create_apex_class 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_apex_class, this is the rule to start with:
sf_create_apex_class 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Salesforce Metadata Mcp, apply this rule, and every sf_create_apex_class call is checked against it from then on.
Questions about sf_create_apex_class
Creates and deploys an Apex class to the Salesforce org using the Metadata API. Accepts the full Apex source code including the class declaration. Use for any type of Apex class: service classes, controllers, batch classes, schedulable classes, queueable classes, test utilities, etc. IMPORTANT — If this class will be used as an Agentforce agent action: it MUST contain a public static method annotated with @InvocableMethod. Classes without @InvocableMethod cannot be invoked by agents and will silently fail at runtime. Example minimum structure: public class MyClass { @InvocableMethod(label=. It is categorised as a Execute tool in the Salesforce Metadata Mcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Salesforce Metadata MCP server in PolicyLayer and add a rule for sf_create_apex_class: 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_apex_class 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 sf_create_apex_class 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_apex_class. 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_apex_class 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.
Across the catalogue