Back to search
100
MCP v0.4.0 streamable-http

XFMS — Model Source

dev.xpansion/xfms

Pick the right LLM for any task. Ranked shortlist with rationale across 8 evaluators.

Uptime
—
no direct probes in 30d
Response
365ms
last probe
Tools
5
callable
Resources
0
readable
Prompts
0
available
Primary URL
https://xfms.vercel.app/mcp/

Tools · 5

rank

Rank LLMs for a stated purpose. Returns a shortlist with weights, scores, and plain-English rationale per pick. Use when the user wants to see and compare alternatives, not just one answer.

pick

Return the single best LLM for a stated purpose. Concise output, no list. Use when the user has settled on the criteria and just wants one answer.

discover

Show which quality dimensions matter for a stated purpose, WITHOUT ranking any models. Returns the inferred weights and the discovery-walk trace. Useful for understanding how XFMS interprets the purpo…

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. Generates 5 representative test queries (auto-expands to 10 or 15 i…

compare

Run a live A/B test between 2–5 user-specified models for a stated purpose. NO ranking step — the supplied model_ids ARE the candidate set. Generates 5 representative test queries from the purpose, ru…

How to use

Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "xfms_—_model_source": {
      "url": "https://xfms.vercel.app/mcp/",
      "transport": "streamable-http"
    }
  }
}