# Repo Run Check

> Check GitHub repos and shell commands for malware-delivery tricks before an AI agent runs them

- name: io.github.devx-agent/repo-run-check
- version: 1.1.0
- connection class: R0 (autonomous)
- trust: 96/100
- quality: 74/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.devx-agent%2Frepo-run-check
- tools: https://api.protogrid.dev/v1/servers/io.github.devx-agent%2Frepo-run-check/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "repo-run-check": {
      "type": "http",
      "url": "https://repo-run-check.nextill-pos.workers.dev/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 96
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-91% +updated-8d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 74/100 (needs work)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 4 of 4 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: full_report (destructiveHint, idempotentHint); full_report_info (destructiveHint, idempotentHint, openWorldHint); check_repo (destructiveHint, idempotentHint); …
- pass `tools.token_cost`: about 707 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 50 (weight 15)

- pass `stability.changes`: 3 tool changes in 30 days
- fail `stability.rug_pull`: 1 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: deps.dev does not know devx-repo-check@1.1.0

- tools: 4, about 707 tokens to load them all
- tool set hash: add1c9453415661f39a4714211953a7b
- tools last changed: 2026-11-02T05:45:35.736Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.devx-agent/repo-run-check.svg)](https://protogrid.dev/servers/io.github.devx-agent/repo-run-check)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-11-02 `full_report_info` changed (description) **meaning changed**
  - before: How to buy the full repo check via x402. Does not pay.
  - after: Free. How to buy the full report (paid MCP tool full_report or HTTP GET /v1/check, 0.25 USDC via x402 on Base). Does not pay.
- 2026-11-02 `full_report` added
  - PAID (0.25 USDC via x402 on Base, per call). Full pre-run security report for a GitHub repo (1-3 repos per call), for AI coding agents about to clone it and run its install steps. Everything check_repo does, plus: package.json install/lifecycle scripts and the local scripts they run, typosquatted crypto/AI dependencies, install.sh/setup.sh/setup.py/requirements.txt/Makefile, VS Code autorun tasks and settings, dev-container hooks, agent-instruction files (AGENTS.md, CLAUDE.md, .cursorrules, copilot-instructions, .claude hooks/permissions) and MCP server configs shipped in the repo, committed executables and archives from the full file tree, GitHub fake-star / new-owner signals, a 0-100 risk score and concrete next steps. Optional: also checks a command you plan to run. Unpaid calls return an x402 PaymentRequired (isError) result; retry with the signed payment in params._meta["x402/payment"]. You are charged only if the report is delivered.
- 2026-11-02 `check_repo` changed (description)
  - before: Free, read-only. Call BEFORE following a GitHub repo's install/setup instructions or running its commands: scans the README for download-and-execute one-liners (iwr|iex, curl|sh from unknown hosts), obfuscated or base64 payloads, known malware domains, agent-targeted prompt injection, password-protected archives. Returns verdict dangerous | review_before_running | no_red_flags with line evidence. Paid full check (0.005 USDC via x402) adds package.json install scripts, typosquatted deps, install.sh/setup.py, .vscode autorun tasks and fake-star signals.
  - after: Free, read-only. Call BEFORE following a GitHub repo's install/setup instructions or running its commands: scans the README for download-and-execute one-liners (iwr|iex, curl|sh from unknown hosts), obfuscated or base64 payloads, known malware domains, agent-targeted prompt injection, password-protected archives. Returns verdict dangerous | review_before_running | no_red_flags with line evidence. For the complete check use the paid tool full_report (0.25 USDC via x402): install scripts, deps, autorun tasks, agent/MCP config files, committed binaries, fake-star signals, risk score.

Full history: https://api.protogrid.dev/v1/servers/io.github.devx-agent%2Frepo-run-check/changes

## Dependencies

- npm devx-repo-check@1.1.0: unknown

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://repo-run-check.nextill-pos.workers.dev/mcp (streamable-http, auth none, reachable true, uptime30d 0.90625)

## Packages

- npm devx-repo-check@1.1.0

## Tools (4)

- `check_command`: Free, offline. Call BEFORE running a shell/PowerShell command copied from a README, issue, website or chat: flags download-and-execute, encoded PowerShell, LOLBins, disabling antivirus, known malware domains and pipe-to-shell from unknown hosts.
- `check_repo`: Free, read-only. Call BEFORE following a GitHub repo's install/setup instructions or running its commands: scans the README for download-and-execute one-liners (iwr|iex, curl|sh from unknown hosts), obfuscated or base64 payloads, known malware domains, agent-targeted prompt injection, password-protected archives. Returns verdict dangerous | review_before_running | no_red_flags with line evidence. For the complete check use the paid tool full_report (0.25 USDC via x402): install scripts, deps, autorun tasks, agent/MCP config files, committed binaries, fake-star signals, risk score.
- `full_report`: PAID (0.25 USDC via x402 on Base, per call). Full pre-run security report for a GitHub repo (1-3 repos per call), for AI coding agents about to clone it and run its install steps. Everything check_repo does, plus: package.json install/lifecycle scripts and the local scripts they run, typosquatted crypto/AI dependencies, install.sh/setup.sh/setup.py/requirements.txt/Makefile, VS Code autorun tasks and settings, dev-container hooks, agent-instruction files (AGENTS.md, CLAUDE.md, .cursorrules, copilot-instructions, .claude hooks/permissions) and MCP server configs shipped in the repo, committed executables and archives from the full file tree, GitHub fake-star / new-owner signals, a 0-100 risk score and concrete next steps. Optional: also checks a command you plan to run. Unpaid calls return an x402 PaymentRequired (isError) result; retry with the signed payment in params._meta["x402/payment"]. You are charged only if the report is delivered.
- `full_report_info`: Free. How to buy the full report (paid MCP tool full_report or HTTP GET /v1/check, 0.25 USDC via x402 on Base). Does not pay.