Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "strategy-lab": {
      "type": "http",
      "url": "https://kellyruns.xyz/mcp"
    }
  }
}

claude mcp add --transport http strategy-lab https://kellyruns.xyz/mcp

[mcp_servers.strategy-lab]
url = "https://kellyruns.xyz/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "strategy-lab": {
      "type": "remote",
      "url": "https://kellyruns.xyz/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "strategy-lab": {
      "type": "http",
      "url": "https://kellyruns.xyz/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=strategy-lab&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8va2VsbHlydW5zLnh5ei9tY3AifQ%3D%3D"
}

{
  "servers": {
    "strategy-lab": {
      "type": "http",
      "url": "https://kellyruns.xyz/mcp"
    }
  }
}

{
  "mcpServers": {
    "strategy-lab": {
      "httpUrl": "https://kellyruns.xyz/mcp"
    }
  }
}

extensions:
  "strategy-lab":
    enabled: true
    name: "strategy-lab"
    type: streamable_http
    uri: "https://kellyruns.xyz/mcp"
    timeout: 300

Quality 79 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene71 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
fail
tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_agent_state (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_lab_summary (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_strategy (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
pass
tools.token_costabout 442 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changesno tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

5 tools, about 442 tokens to load them all · tool set ad5cb9d66868 · checked 2026-10-20 19:10 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 67 / 100

unreachable

provenance100

liveness0

freshness85

hygiene100

+repository +namespace-matches-repo +dns-namespace +website -unreachable(4 failures) ~updated-68d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://kellyruns.xyz/mcp` streamable-http	none	no (4 failures)	96%	580 ms	2025-06-18	2026-10-14

Tools (5)

`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.
`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.
`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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "xyz.kellyruns/strategy-lab",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://kellyruns.xyz/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.1.0",
  "repository": {
    "url": "https://github.com/kellyruns/kellyruns",
    "source": "github"
  },
  "websiteUrl": "https://kellyruns.xyz/how-it-works",
  "description": "Stress-test lowcap, perp and LP strategies. Returns the full distribution and a reproduction seed."
}