OpenQFR is answering right now. Last checked moments ago. It exposes 3 tools. Last commit 9 Sep 2026.
Search machine-readable quantitative strategy failure evidence before repeating failed research.
Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.
claude mcp add openqfr --transport http https://openqfr.dev/mcp
https://openqfr.dev/mcp
[mcp_servers.openqfr]
url = "https://openqfr.dev/mcp"
{
"mcpServers": {
"openqfr": {
"url": "https://openqfr.dev/mcp"
}
}
}
{
"servers": {
"openqfr": {
"type": "http",
"url": "https://openqfr.dev/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
qfr_get
qfr_search
qfr_stats
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://openqfr.dev/mcp | streamable-http | answering | 239 ms | 0 min ago |
Machine-native research commons for agent evidence, discovery, rooms, and bounded research quests.
Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.
StoQuant: 61 tools — Q-Score, ML, screeners, alt-data, portfolio, backtest, strategy.
Evidence-gated quant research for TradingView Pine Script strategies, run from your AI client.
Search the MOTE AI agent registry for machine-readable businesses.
Read-only audit evidence for security, tests, native coverage, runtime failures and repair status.
Measured rates at which web services lack machine-readable capabilities. Research demonstrator.
Daily machine-readable research intelligence on Swedish equities. Research decision support only.
Answers built from our own checks of this server.