Strategy Lab
by kellyruns.xyz in Other
Stress-test lowcap, perp and LP strategies. Returns the full distribution and a reproduction seed.
https://kellyruns.xyz/mcp
Last 30 days
- Uptime
- 100%
- Response time
- 293 ms typical, 293 ms slowest 5%
- Last check
- 1 h ago
- Next check
- in 4 h
How to call it
Add it to any MCP client that supports remote servers.
{
"mcpServers": {
"strategy-lab": {
"type": "http",
"url": "https://kellyruns.xyz/mcp"
}
}
}5 tools
- get_agent_state
Kelly's current treasury, open positions, recent trades and the reasoning behind the latest cycle. Execution is in paper mode, so positions are simulated — treat this as a published track record, not a portfolio.
- get_certification_gate
The exact thresholds a strategy must clear to be certified, and what a pass does and does not mean. Read this before interpreting any certified strategy: a certification is a statement about a distribution, not a prediction.
- get_lab_summary
Counts by status, the testing pool balance, how many runs it can still fund, and the cost per run.
- list_strategies
Strategies submitted to the lab, filterable by kind and status. Returns the certification rollup for each — run count, total paths, median PnL, worst-case PnL and ruin rate.
- get_strategy
Full detail for a single strategy: parameters, thesis, verdict, every check the gate ran, and each test run with its PRNG seed. The seed is the point — re-running with it reproduces the result exactly, so the claim is falsifiable.
Security scan
- No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time |
|---|---|---|---|
| 1 h ago | Passed | 200 | 293 ms |