Fake Star Audit

Name: Fake Star Audit
Author: ardev-lab

by ardev-labcommunityv0.1.2

An MCP wrapper around a GitHub star-audit tool that checks a repository for signs of fake or injected stars and returns a LOW/MEDIUM/HIGH risk verdict with evidence. It runs locally over stdio and exposes the `audit_repo` tool for analyzing one repo at a time.

From the registry: Transparent rule-based GitHub fake-star detector — LOW/MEDIUM/HIGH with per-rule evidence.

GitHub Repository

Install & configure

Prerequisites

optional
Install uv
Install the `uv` tool to run the published package via `uvx`, which is the simplest MCP setup described in the README.
https://docs.astral.sh/uv/

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `fake-star-audit` MCP server into my current AI client (that's you).

Optional prerequisites:
- Install uv — Install the `uv` tool to run the published package via `uvx`, which is the simplest MCP setup described in the README. (https://docs.astral.sh/uv/)

Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["fake-star-audit"]

Note: The README states the MCP server runs over stdio, opens no network server, and reads no environment variables. A local-checkout alternative exists (`python3 /absolute/path/to/fake-star-audit/mcp_server.py`) but the portable package-based `uvx fake-star-audit` path is preferred.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: The README states the MCP server runs over stdio, opens no network server, and reads no environment variables. A local-checkout alternative exists (`python3 /absolute/path/to/fake-star-audit/mcp_server.py`) but the portable package-based `uvx fake-star-audit` path is preferred.