AI agents use fork_repository to create or update resources in Gitee — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gitee environment.
Forking a repository creates new data (a duplicate repository) in the user's account, making it a Write operation rather than Read. While the action itself is reversible (the fork can be deleted), it creates significant new resources and could consume quotas or storage. The severity is high because mass forking could exhaust rate limits, consume storage, or be used to distribute malicious copies of repositories.
From the tool's definition Tool name 'fork_repository' and description 'Fork Gitee 仓库' (Fork Gitee repository). Forking creates a new copy of a repository under the user's account, which is a permanent data creation action.
Documented attack patterns abuse exactly the kind of access fork_repository gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gitee, and nothing reaches the server without passing your rules. This is the rule we recommend for fork_repository:
{
"version": "1",
"default": "deny",
"tools": {
"fork_repository": {
"limits": [
{
"counter": "fork_repository_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}fork_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.
Fork Gitee 仓库. It is categorised as a Write tool in the Gitee MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gitee MCP server in PolicyLayer and add a rule for fork_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 Gitee. Nothing to install.
fork_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 fork_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 fork_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.
fork_repository is provided by the Gitee MCP server (normal-coder/gitee-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gitee, 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.
20 Gitee tools catalogued and risk-classified — across an index of 43,000+ MCP servers.