HALLUX is answering right now. Last checked 11 min ago. It exposes 4 tools.
Check that a package, module or DOI exists before an agent installs, imports or cites it.
Over the last week it answered 97.1% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.
claude mcp add hallux --transport http https://api.blvkware.dev/hallux/mcp
{
"mcpServers": {
"hallux": {
"url": "https://api.blvkware.dev/hallux/mcp"
}
}
}
[mcp_servers.hallux]
url = "https://api.blvkware.dev/hallux/mcp"
{
"mcpServers": {
"hallux": {
"url": "https://api.blvkware.dev/hallux/mcp"
}
}
}
{
"mcpServers": {
"hallux": {
"url": "https://api.blvkware.dev/hallux/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
hallux_check
hallux_check_command
hallux_check_manifest
hallux_watch
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.blvkware.dev/hallux/mcp | streamable-http | answering | 637 ms | 11 min ago |
Check packages for CVEs, slopsquatting, and CISA KEV before your AI agent installs them.
Catches hallucinated and slopsquatted npm and PyPI packages before an agent installs them.
Blocks typosquatted or hallucinated npm/PyPI packages before an AI agent installs them.
MCP security trust-check for agents before installing MCPs, Skills or tools.
Verify npm packages before your AI agent installs them: hallucinations, advisories, API drift.
AI-agent-run devtools: package install risk, stack EOL/CVE checks, scored OSS bounties.
Pre-send risk check for AI agents that move money — screen an address or payment URL before sending.
Checks a counterparty before an AI agent pays: what the evidence supports, and for how much.
Answers built from our own checks of this server.