Firedrill is answering right now. Last checked 6 min ago. Last commit 18 Oct 2026.
Operate simulations and inspect retained evidence with Firedrill.
Today is the operative word: we check Firedrill 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 6 min ago.
claude mcp add firedrill --transport http https://mcp.firedrill.run/mcp
https://mcp.firedrill.run/mcp
[mcp_servers.firedrill]
url = "https://mcp.firedrill.run/mcp"
{
"mcpServers": {
"firedrill": {
"url": "https://mcp.firedrill.run/mcp"
}
}
}
{
"servers": {
"firedrill": {
"type": "http",
"url": "https://mcp.firedrill.run/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.firedrill.run/mcp | streamable-http | sign-in | 181 ms | 6 min ago |
Build, run, inspect, and verify finite-element simulations with AgentFEM.
Construct, inspect, visualize, and simulate evidence-backed ODE models with BioMASS
Inspect and operate Next.js Redis caches: health, tag state, SWR simulation, safe invalidation.
AI BVF: review AI proposals with Stop, Fix or Accelerate, evidence gaps and next actions.
Read-only public website inspection: evidence-backed Machine Presence observations with uncertainty.
Create and run AI evaluations, record traces, and inspect results with scoped organization access.
Find lab-report identities and clinical research with dated sources and evidence limitations.
Trust-aware agent memory with evidence-backed recall, self-inspection, and audit history.
Answers built from our own checks of this server.