Fork a GitHub repository to your account or specified organization
AI agents use fork_repository to create or update resources in Server Puppeteer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Server Puppeteer environment.
Forking a repository creates a new copy under the specified account/organization. This is a Write operation (creates new data) rather than Destructive, as the original repository is unaffected. However, severity is high because it can create unauthorized copies of private/sensitive repositories under an attacker-controlled account, potentially exposing proprietary code.
From the tool's definition Fork a GitHub repository to your account or specified organization
Attacks that exploit this kind of access
Fork a GitHub repository to your account or specified organization. It is categorised as a Write tool in the Server Puppeteer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Server Puppeteer 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 Server Puppeteer. 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 Server Puppeteer MCP server (@hisma/server-puppeteer). 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 →