save_workflow_preferences · Codecks MCP: Risk & Policy

WHAT IT DOES

What save_workflow_preferences does on Codecks

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

WHY IT NEEDS A POLICY

Why save_workflow_preferences needs a policy

The tool creates or modifies preferences data (reversible write operation). While not destructive and not immediately severe, saving workflow patterns without authentication could allow an agent to alter team workflow configurations. Severity is medium rather than high because preferences are typically recoverable and don't directly execute external operations or delete data.

From the tool's definition Tool name 'save_workflow_preferences' and description indicate it persists data ('Save observed workflow patterns'). This is a write operation that modifies stored preferences/settings.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_workflow_preferences Rate-limited

save_workflow_preferences 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": {
    "save_workflow_preferences": {
      "limits": [
        {
          "counter": "save_workflow_preferences_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 Codecks, so you can run agents against it safely.

FAQ

Questions about save_workflow_preferences

What does the save_workflow_preferences tool do? +

Save observed workflow patterns from current session. No auth needed. It is categorised as a Write tool in the Codecks MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_workflow_preferences? +

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

What risk level is save_workflow_preferences? +

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

Can I rate-limit save_workflow_preferences? +

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

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

save_workflow_preferences is provided by the Codecks MCP server (rangogamedev/codecks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.