AI agents use create_release 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.
Creating a release is a write operation that creates or modifies repository metadata (release/tag objects) and is reversible (releases can be deleted or modified). This does not meet the threshold for Destructive (which requires irreversibility) or Execute (which would apply to running arbitrary code).
From the tool's definition Tool name 'create_release' and description 'Create a new release for a GitLab project' indicate creation of a new release artifact/tag in a repository, which is a reversible write operation.
Documented attack patterns abuse exactly the kind of access create_release 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_release:
{
"version": "1",
"default": "deny",
"tools": {
"create_release": {
"limits": [
{
"counter": "create_release_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_release 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 release for a 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_release: 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_release 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_release 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_release. 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_release 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.