Batcave Detective Basic is answering right now. Last checked 3 min ago. It exposes 5 tools.
Evidence-bound second-opinion audit of an agent conclusion against caller-supplied evidence.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 4 September 2026. No other catalogue keeps this.
Over the last week it answered 44.6% 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 3 min ago.
claude mcp add batcave-detective --transport http https://subsidy-stylized-unaligned.ngrok-free.dev/mcp
{
"mcpServers": {
"batcave-detective": {
"url": "https://subsidy-stylized-unaligned.ngrok-free.dev/mcp"
}
}
}
[mcp_servers.batcave-detective]
url = "https://subsidy-stylized-unaligned.ngrok-free.dev/mcp"
{
"mcpServers": {
"batcave-detective": {
"url": "https://subsidy-stylized-unaligned.ngrok-free.dev/mcp"
}
}
}
{
"mcpServers": {
"batcave-detective": {
"url": "https://subsidy-stylized-unaligned.ngrok-free.dev/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
detective_basic
evidence_judge
json_doctor
run_python
scenario_council
Tools this server used to expose. Anything built against them stopped working on the day they went.
audit_claims
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://subsidy-stylized-unaligned.ngrok-free.dev/mcp | streamable-http | answering | 709 ms | 3 min ago |
Audit agent-distribution surfaces and create an evidence-based distribution plan.
Trust-aware agent memory with evidence-backed recall, self-inspection, and audit history.
Evidence-based supplement research, dosing, safety, and interactions as agent-callable tools.
Bounded Scala compiler, build, test, type, effect, symbol, and SemanticDB evidence for agents.
Evidence-bound REW measurement, analysis, conservative EQ, DSP, and listening-test tools.
MERCATOR Verify: evidence-backed verification and decision support for autonomous agents.
Audit agent skills/prompts against 8 supply-chain attack patterns. Deterministic, no-LLM scanner.
A second opinion, in one call, from a desk where an answer is allowed to be no.
Answers built from our own checks of this server.