INDIVIDUAL MCP TOOL

benchmark

Run a live A/B test against the engine's TOP 3 PICKS for a stated purpose — the engine chooses the candidates from the full catalog.

xpansion.devnone authenticationAvailability not checked

Input schema

{}

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.

CONNECT WITH APPROVAL

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

Codex

~/.codex/config.toml

[mcp_servers.xfms]
url = "https://xfms.vercel.app/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "xfms": {
      "type": "http",
      "url": "https://xfms.vercel.app/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: xfms
Remote MCP URL: https://xfms.vercel.app/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": {
    "xfms": {
      "url": "https://xfms.vercel.app/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "xfms": {
      "type": "http",
      "url": "https://xfms.vercel.app/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "xfms",
  "transport": "streamable-http",
  "url": "https://xfms.vercel.app/mcp"
}

MCP Inspector

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

rank — Rank LLMs for a stated purpose.
pick — Return the single best LLM for a stated purpose.
discover — Show which quality dimensions matter for a stated purpose, WITHOUT ranking any models.
compare — Run a live A/B test between 2–5 user-specified models for a stated purpose.