# Rayyer220 Regimen MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.rayyer220%2Fregimen
Registry id: `mcp-registry/io.github.rayyer220/regimen`
Status: live (checked 2026-10-27T04:26:33.504Z)

## Verdict

Rayyer220 Regimen MCP server answered 99.85% of Glimind's liveness checks over 30 days, better than 25% of MCP servers, with 1122 ms median handshake and 1 outage in 90 days. Its agent-readiness grade is A (91/100) across 4 tools, costing an agent about 2,731 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.85% | 25% of MCP servers |
| Median handshake latency | 1122 ms | 15% of MCP servers |
| p95 handshake latency | 3104 ms | — |
| Checks in 30 days | 4,678 | — |
| Outages, 90 days | 1 | — |
| Median recovery | 25.5 h | — |
| Agent-readiness score | 91/100 (A) | 71% of MCP servers |
| Tools | 4 | — |
| Tool-list size for an agent | ~2,731 tokens | 47% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "rayyer220-regimen-mcp-server": {
      "type": "http",
      "url": "https://regimen-nu.vercel.app/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http rayyer220-regimen-mcp-server https://regimen-nu.vercel.app/mcp
```

## Tools (4)

- `regimen_describe_factors`: List the market-condition factors Regimen slices performance by, with units, the upstream operation each is read from, and how it is bucketed. Call this when yo
- `regimen_evaluate_track_record`: Answer whether a trading strategy’s measured performance is distinguishable from luck. Returns the Probabilistic Sharpe Ratio (the probability the true Sharpe b
- `regimen_regime_map`: Break a strategy’s returns down by the market conditions that held on each date — volatility, funding, open interest, positioning, sentiment, trend state — and 
- `regimen_self_attack`: Run Regimen’s own analysis against controls whose answer is known in advance: the strategy’s returns with the edge mathematically removed, and a simulated popul

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
