Create a new GitHub repository in your account
AI agents use create_repository to create or update resources in Server Github — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Server Github environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | Yes | Repository name |
private | boolean | — | Whether the repository should be private |
autoInit | boolean | — | Initialize with README.md |
description | string | — | Repository description |
Parameters from the server's own tool schema.
Creating a repository is a write operation that modifies the user's GitHub account state by adding a new resource. While reversible (unlike destructive operations), it has high blast radius if misused by an agent — an agent could spam repository creation, exhaust quota limits, or create repositories with sensitive names/configurations.
From the tool's definition Tool name is 'create_repository' and description states 'Create a new GitHub repository in your account' — this creates a new resource (repository) with side effects that are reversible (repository can be deleted).
Attacks that exploit this kind of access
Create a new GitHub repository in your account. It is categorised as a Write tool in the Server Github MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
create_repository accepts 4 parameters: name, private, autoInit, description. Required: name. The full parameter table on this page comes from the server's own tool schema.
Register the Server Github MCP server in PolicyLayer and add a rule for create_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 Github. Nothing to install.
create_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 create_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 create_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.
create_repository is provided by the Server Github MCP server (@iflow-mcp/server-github). 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 →