This record as markdown: /tools/io-github-portel-dev-ncp/fork-repository.md
What fork_repository does on Ncp
AI agents use fork_repository to create or update resources in Ncp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ncp environment.
Why fork_repository is rated Medium
Forking a repository creates a new resource (a copy of an existing repository under the user's account) but is non-destructive and reversible—the fork can be deleted or the original remains intact. This is a Write operation rather than Execute because it doesn't run code or arbitrary operations; it performs a specific repository management action.
From the tool's definition Tool name 'fork_repository' and description 'Fork a GitHub repository' indicate creating a new repository resource on GitHub, which is a reversible write operation.
Attacks that exploit this kind of access
The rule that runs fork_repository safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ncp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fork_repository, this is the rule to start with:
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.
The button opens the PolicyLayer dashboard: create your workspace, connect Ncp, apply this rule, and every fork_repository call is checked against it from then on.
Questions about fork_repository
Fork a GitHub repository. It is categorised as a Write tool in the Ncp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ncp 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 Ncp. 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 Ncp MCP server (@portel/ncp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ncp, and thousands of servers like it.
This server
Across the catalogue