Medium Risk

gitlab_create_work_item

Create a work item of type issue, task, incident, test_case, epic, key_result, objective, requirement, or ticket.

How to control gitlab_create_work_item ↓

What gitlab_create_work_item does on Gitlab

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

Medium Risk

Why gitlab_create_work_item needs a policy

This tool creates new GitLab work items, which modifies the GitLab project state by adding new records. This is a Write operation because it creates data reversibly (work items can be deleted/archived).

From the tool's definition Tool creates work items of various types (issue, task, incident, test_case, epic, key_result, objective, requirement, ticket) via GitLab API. The description explicitly states 'Create a work item', which is a reversible data creation operation.

Documented attack patterns abuse exactly the kind of access gitlab_create_work_item gives an agent:

How to control gitlab_create_work_item

PolicyLayer is an MCP gateway — it sits between your AI agents and Gitlab, and nothing reaches the server without passing your rules. This is the rule we recommend for gitlab_create_work_item:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "gitlab_create_work_item": {
      "limits": [
        {
          "counter": "gitlab_create_work_item_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

gitlab_create_work_item 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.

  1. Create a free account and register Gitlab — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about gitlab_create_work_item

What does the gitlab_create_work_item tool do? +

Create a work item of type issue, task, incident, test_case, epic, key_result, objective, requirement, or ticket. It is categorised as a Write tool in the 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 gitlab_create_work_item? +

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

What risk level is gitlab_create_work_item? +

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

Can I rate-limit gitlab_create_work_item? +

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

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

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

Enforce policy on every Gitlab tool call.

Start from Gitlab, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

190 Gitlab tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.