list_starred_repositories
A read tool on the GitHub MCP server.
This record as markdown: /tools/github/list-starred-repositories.md
What list_starred_repositories does on GitHub
AI agents call list_starred_repositories to retrieve information from GitHub without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
page | number | — | Page number for pagination (min 1) |
sort | string | — | How to sort the results. Can be either 'created' (when the repository was starred) or 'updated' (when the repository was last pushed to). |
perPage | number | — | Results per page for pagination (min 1, max 100) |
username | string | — | Username to list starred repositories for. Defaults to the authenticated user. |
direction | string | — | The direction to sort the results by. |
Parameters from the server's own tool schema.
Why list_starred_repositories is rated Low
This tool performs a read-only operation that retrieves information about starred repositories. It has no side effects, does not modify data, and does not execute code or trigger external operations. The blast radius of misuse is minimal—an AI agent could only retrieve a list of repositories, which is informational data. This is a standard Read category operation.
From the tool's definition Tool name 'list_starred_repositories' and description 'List starred repositories' indicate a query operation that retrieves data without modification.
Attacks that exploit this kind of access
The rule that runs list_starred_repositories safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GitHub, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_starred_repositories, this is the rule to start with:
list_starred_repositories is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect GitHub, apply this rule, and every list_starred_repositories call is checked against it from then on.
Questions about list_starred_repositories
list_starred_repositories is a read tool on the GitHub MCP server. It is categorised as a Read tool in the GitHub MCP Server, which means it retrieves data without modifying state.
list_starred_repositories accepts 5 parameters: page, sort, perPage, username, direction. The full parameter table on this page comes from the server's own tool schema.
Register the GitHub MCP server in PolicyLayer and add a rule for list_starred_repositories: 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 GitHub. Nothing to install.
list_starred_repositories is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_starred_repositories 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 list_starred_repositories. 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.
list_starred_repositories is provided by the GitHub MCP server (oci:ghcr.io/github/github-mcp-server:1.3.0). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GitHub, and thousands of servers like it.
This server
Across the catalogue