AI agents use create_repository 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.
This tool creates a new project/repository, which is a reversible Write operation. While it consumes resources and creates a new entity in GitLab, the action can be undone by deleting the project. It does not execute arbitrary code, delete data, or move money, placing it firmly in the Write category.
From the tool's definition Tool name 'create_repository' and description 'Create a new GitLab project' indicate creation of a new resource in GitLab.
Documented attack patterns abuse exactly the kind of access create_repository gives an agent:
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 create_repository:
{
"version": "1",
"default": "deny",
"tools": {
"create_repository": {
"limits": [
{
"counter": "create_repository_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_repository 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.
Free to start. No card required.
Create a new GitLab project. 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.
Register the Gitlab MCP server in PolicyLayer and add a rule for create_repository: 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.
create_repository is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_repository 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.
Set action: deny in the PolicyLayer policy for create_repository. 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.
create_repository is provided by the Gitlab MCP server (yoda-digital/mcp-gitlab-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 88 Gitlab tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
88 Gitlab tools catalogued and risk-classified — across an index of 42,500+ MCP servers.