← kellyruns.xyz

INDIVIDUAL MCP TOOL

get_lab_summary

Counts by status, the testing pool balance, how many runs it can still fund, and the cost per run.

kellyruns.xyznone authenticationAvailability not checked

LIVE ENDPOINT

https://kellyruns.xyz/mcp

No auth detected

Connect to this endpoint to inspect the live schema for get_lab_summary and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Inferred read-only · medium confidence · heuristic, not a guarantee.

  • No write-capable action terms were found; this is not proof that invocation has no side effects.

Parent server

kellyruns.xyz

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.kelly]
url = "https://kellyruns.xyz/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "kelly": {
      "type": "http",
      "url": "https://kellyruns.xyz/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: kelly
Remote MCP URL: https://kellyruns.xyz/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "kelly": {
      "url": "https://kellyruns.xyz/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "kelly": {
      "type": "http",
      "url": "https://kellyruns.xyz/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "kelly",
  "transport": "streamable-http",
  "url": "https://kellyruns.xyz/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

  • get_agent_state — Kelly's current treasury, open positions, recent trades and the reasoning behind the latest cycle.
  • get_certification_gate — The exact thresholds a strategy must clear to be certified, and what a pass does and does not mean.
  • list_strategies — Strategies submitted to the lab, filterable by kind and status.
  • get_strategy — Full detail for a single strategy: parameters, thesis, verdict, every check the gate ran, and each test run with its PRNG seed.