MCP serverdev.xpansion/xfms

Pick the right LLM for any task.

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

UNRATEDActivestreamable-httpxfms.vercel.app

Overview

Score?

UNRATED 0.672

of what a free look can see, on 30 looks

Looks

last 3 hr ago

Tools

changed 11 days ago

URL

xfms.vercel.app/mcp/

streamable-http

Says it is

xfms 1.30.0

protocol 2025-06-18

In the record since

32 days ago

0median 0.606 · this server 0.672 · highest on record 0.8561

The tools this server lists, read out of the definition it returned
Tool	Schema
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-e	input · output
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	input · output
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	input · output
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.	input · output
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 on	input · output

Verify it yourselfnpx teppi-check https://xfms.vercel.app/mcp/curl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2AK9YRYT0GQXP3P5EKKE