MCP Kill-Chain Research — Stage 1 (Identity ≠ Behavior) is answering right now. Last checked 10 min ago. It exposes 1 tools.
Security research: MCP registries verify identity, not tool behavior. See gtfo.dev.
Today is the operative word: we check MCP Kill-Chain Research — Stage 1 (Identity ≠ Behavior) every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.
claude mcp add mcp-killchain-stage1-weather --transport http https://ailm.gtfo.dev/mcp
{
"mcpServers": {
"mcp-killchain-stage1-weather": {
"url": "https://ailm.gtfo.dev/mcp"
}
}
}
[mcp_servers.mcp-killchain-stage1-weather]
url = "https://ailm.gtfo.dev/mcp"
{
"mcpServers": {
"mcp-killchain-stage1-weather": {
"url": "https://ailm.gtfo.dev/mcp"
}
}
}
{
"mcpServers": {
"mcp-killchain-stage1-weather": {
"url": "https://ailm.gtfo.dev/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
get_weather
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://ailm.gtfo.dev/mcp | streamable-http | answering | 168 ms | 10 min ago |
Hyperion — MCP tool marketplace for AI agents: web, OSINT, security, research via one key.
PoC: Open Registry supply chain — unvetted server listing (security research)
Trust verification for MCP servers. Check scores, scan for security issues, search 4,200+ servers.
Search and install 20,000+ security-graded MCP servers and agent skills.
MCP security firewall: vet tool definitions before they reach the model.
PoC benign MCP server for update-hijack security research
Abnormal Security MCP: threats, search, remediation, ATO cases, vendor/BEC, and evidence download.
Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases.
Answers built from our own checks of this server.