patch_lead · Smokeball MCP: Risk & Policy

WHAT IT DOES

What patch_lead does on Smokeball

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

WHY IT NEEDS A POLICY

Why patch_lead needs a policy

This tool creates or modifies data (lead records) in a reversible manner. The updates to lead status and assignment can be changed or undone, making it a Write operation rather than Destructive. While it modifies business-critical CRM data that could affect law firm operations, the reversibility and bounded scope (lead fields only, not matters or financial records) place it at medium severity rather than high.

From the tool's definition Tool name 'patch_lead' and description 'Partially update a lead status or assignment (PATCH)' indicates modifying lead records. The PATCH HTTP verb and mention of updating 'status or assignment' confirm reversible data modification without permanent deletion.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

patch_lead Rate-limited

patch_lead 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": {
    "patch_lead": {
      "limits": [
        {
          "counter": "patch_lead_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Smokeball, so you can run agents against it safely.

FAQ

Questions about patch_lead

What does the patch_lead tool do? +

Partially update a lead status or assignment (PATCH). Use update_lead for notes. It is categorised as a Write tool in the Smokeball MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on patch_lead? +

Register the Smokeball MCP server in PolicyLayer and add a rule for patch_lead: 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 Smokeball. Nothing to install.

What risk level is patch_lead? +

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

Can I rate-limit patch_lead? +

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

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

patch_lead is provided by the Smokeball MCP server (rosenadvertising/smokeball-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.