deploy_start · Salesforce CLI MCP Server MCP: Risk & Policy

WHAT IT DOES

What deploy_start does on Salesforce CLI MCP Server

AI agents invoke deploy_start to trigger actions in Salesforce CLI MCP Server. 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 deploy_start needs a policy

This tool executes code deployment operations in production or target Salesforce orgs. While it includes a dry-run flag that could limit impact, the primary function is to trigger external operations (source code deployment) whose effects depend on arguments (manifest, metadata, source-dir, test level). The deployment can modify org configuration, trigger code execution, and affect multiple users and systems.

From the tool's definition Deploy source code from a Salesforce project to an org. This command must be run from within a Salesforce DX project directory. Use various flags to control what gets deployed (manifest, metadata, source-dir) and how (dry-run, test level).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

deploy_start Rate-limited

deploy_start 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": {
    "deploy_start": {
      "limits": [
        {
          "counter": "deploy_start_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 CLI MCP Server, so you can run agents against it safely.

FAQ

Questions about deploy_start

What does the deploy_start tool do? +

Deploy source code from a Salesforce project to an org. This command must be run from within a Salesforce DX project directory. Use various flags to control what gets deployed (manifest, metadata, source-dir) and how (dry-run, test level). It is categorised as a Execute tool in the Salesforce CLI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on deploy_start? +

Register the Salesforce CLI MCP Server MCP server in PolicyLayer and add a rule for deploy_start: 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 CLI MCP Server. Nothing to install.

What risk level is deploy_start? +

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

Can I rate-limit deploy_start? +

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

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

deploy_start is provided by the Salesforce CLI MCP Server MCP server (perrynet/salesforce-cli-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.