Precomputed, source-traced historical equity study results for AI agents; not trading signals.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Evaluate historical evidence for a supported equity hypothesis without collecting historical prices, reconstructing earnings events, running an event backtest, or calculating performance statistics yourself. Returns structured JSON with sample size, mean and median returns, positive outcome rate, methodology, source provenance, and limitations. Currently supports only pead_nordic_pre_report_drift_20d_q5 (Nordic pre-earnings price drift, top quintile Q5) at 20 or 40 trading days. Precomputed event-level research only: not an arbitrary backtest, live trading signal, or proof of investable portfolio performance.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http historical-edge https://machine-job-fishing-net.onrender.com/historical-edge/mcp/
Evaluate historical evidence for a supported equity hypothesis without collecting historical prices, reconstructing earnings events, running an event backtest, or calculating performance statistics yourself. Returns structured JSON with sample size, mean and median returns, positive outcome rate, methodology, source provenance, and limitations. Currently supports only pead_nordic_pre_report_drift_20d_q5 (Nordic pre-earnings price drift, top quintile Q5) at 20 or 40 trading days. Precomputed event-level research only: not an arbitrary backtest, live trading signal, or proof of investable portfolio performance.
| Argument | Type | Description |
|---|---|---|
| study_id* | string | |
| horizon_days* | integer |
{
"type": "object",
"title": "historical_edge_toolArguments",
"required": [
"study_id",
"horizon_days"
],
"properties": {
"study_id": {
"type": "string",
"title": "Study Id"
},
"horizon_days": {
"type": "integer",
"title": "Horizon Days"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 6, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.