Fork a project.
AI agents use fork_project to create or update resources in GitLab MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitLab MCP Server environment.
Forking creates a new project repository derived from the source, which is a reversible write operation (the fork can be deleted). It does not delete or overwrite original data, execute arbitrary code, or involve financial transactions. Severity is medium because forking could be misused to exfiltrate code into attacker-controlled namespaces or create confusion with many unwanted forks.
From the tool's definition Fork a project — creates a new copy of the project in the user's namespace
Attacks that exploit this kind of access
Fork a project. It is categorised as a Write tool in the GitLab MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitLab MCP Server MCP server in PolicyLayer and add a rule for fork_project: 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 MCP Server. Nothing to install.
fork_project 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 fork_project 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 fork_project. 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.
fork_project is provided by the GitLab MCP Server MCP server (skmprb/gitlab-clone-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →