mark_started · Codecks MCP: Risk & Policy

WHAT IT DOES

What mark_started does on Codecks

AI agents use mark_started 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 mark_started needs a policy

This tool modifies card status/state from unstarted to started, which is a reversible Write operation typical of project management systems. It does not delete data (Destructive), execute arbitrary code (Execute), move money (Financial), or retrieve data only (Read). The blast radius is limited to updating a single card's workflow state, making it a low-severity write operation.

From the tool's definition Tool name 'mark_started' and description 'Mark cards as started' indicate modification of card state. Sibling context (create_card, update operations) confirms this is a state-change operation within a project management system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_started Rate-limited

mark_started 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": {
    "mark_started": {
      "limits": [
        {
          "counter": "mark_started_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 mark_started

What does the mark_started tool do? +

Mark cards as started. 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 mark_started? +

Register the Codecks MCP server in PolicyLayer and add a rule for mark_started: 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 mark_started? +

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

Can I rate-limit mark_started? +

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

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

mark_started 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.