createRepository
AI agents use createRepository to create or update resources in GitHubMcpServer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHubMcpServer environment.
This tool creates a new repository, which is a reversible write operation. While it doesn't delete or move money, creating repositories on behalf of a user could have significant consequences (consuming quota, creating unwanted projects, potential for griefing).
From the tool's definition Tool name 'createRepository' in GitHub context; server description states tool enables 'creating repositories' and 'managing repositories'. Creates new data structure (repository) in GitHub. Tool description is empty, reducing confidence slightly.
Attacks that exploit this kind of access
createRepository. It is categorised as a Write tool in the GitHubMcpServer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitHubMcpServer MCP server in PolicyLayer and add a rule for createRepository: 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 GitHubMcpServer. Nothing to install.
createRepository 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 createRepository 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 createRepository. 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.
createRepository is provided by the GitHubMcpServer MCP server (moksh555/githubmcpserver). 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 →