create_iteration · Mcp Gitlab MCP: Risk & Policy

WHAT IT DOES

What create_iteration does on Mcp Gitlab

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

WHY IT NEEDS A POLICY

Why create_iteration needs a policy

Creating an iteration is a write operation that adds new structured data to a group. It is reversible (unlike deletion) and does not execute arbitrary code, trigger pipelines, or move money. The dry_run=true default provides safety but does not change the categorization of the actual operation.

From the tool's definition "Create a new iteration (sprint) in a group" — this creates a new data object in GitLab. The tool modifies project/group state by adding a sprint, which is reversible (iterations can be deleted or edited).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_iteration Rate-limited

create_iteration 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": {
    "create_iteration": {
      "limits": [
        {
          "counter": "create_iteration_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 Mcp Gitlab, so you can run agents against it safely.

FAQ

Questions about create_iteration

What does the create_iteration tool do? +

Create a new iteration (sprint) in a group. start_date and due_date are required (YYYY-MM-DD). dry_run=true by default. It is categorised as a Write tool in the Mcp Gitlab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_iteration? +

Register the Mcp Gitlab MCP server in PolicyLayer and add a rule for create_iteration: 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 Mcp Gitlab. Nothing to install.

What risk level is create_iteration? +

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

Can I rate-limit create_iteration? +

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

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

create_iteration is provided by the Mcp Gitlab MCP server (wanadev/gitlab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.