Docs & AI · Official remote MCP server

The XFMS — Model Source MCP server,
connected in one click.

Pick the right LLM for any task. Ranked shortlist with rationale across 8 evaluators. Connect the official XFMS — Model Source MCP server to Claude, ChatGPT, or Cursor through gate — one gateway URL, no config files, security-checked.

Connect XFMS — Model Source free How it works

Free to start · No credit card · No hosting needed

Use this server

Add XFMS — Model Source to your AI in one minute

Pick your client. Copy, paste, done — or let gate handle sign-ins and policies for you.

claude mcp add --transport http xfms-model-source https://xfms.vercel.app/mcp/

Run in your terminal, then restart Claude Code.

XFMS — Model Source · https://xfms.vercel.app/mcp/

What you can do

What your AI can do with XFMS — Model Source

Real prompts you can type the moment it's connected — no setup, no docs to read.

“Use “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 s.”

“Use “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 a.”

“Use “discover”: Show which quality dimensions matter for a stated purpose, WITHOUT ranking any models. Returns the inferred weights and the discovery-walk t.”

“Use “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. Generat.”

Security check

How secure is the XFMS — Model Source MCP server?

Every server in the gate directory has to pass the same four checks before your AI can touch it. Here's how XFMS — Model Source holds up.

✓ Verified directory serverXFMS — Model Source · xpansion.dev

Official endpoint

Operated by XFMS — Model Source (xpansion.dev) at its documented MCP endpoint — not a third-party mirror or community re-host.

No sign-in needed

This server only exposes public data — no account and no credentials are involved when you connect.

Scanned before it goes live

gate checks every tool for prompt injection, hidden instructions, data-exfiltration hints, and over-broad permissions before the server is available through your gateway.

Watched for drift

If XFMS — Model Source adds or changes tools later, gate re-scans and alerts you — before your AI acts on the change.

Run the free scanner on XFMS — Model Source's server →

How it works

Connected in three steps

Connect your gate

Add one gateway URL to Claude, ChatGPT, or any MCP client. One-time setup, about two minutes.

Pick XFMS — Model Source

Choose XFMS — Model Source in the gate directory. No sign-in needed.

Use it anywhere

XFMS — Model Source's tools are live in every AI client you've connected — with rules and logging built in.

Connect XFMS — Model Source free

Free to start · No credit card · No hosting needed

Straight from the server

The actual tools XFMS — Model Source exposes

Fetched live from the official endpoint and re-checked daily by gate — not marketing copy.

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 s

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 a

discover — Show which quality dimensions matter for a stated purpose, WITHOUT ranking any models. Returns the inferred weights and the discovery-walk t

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. Generat

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.

Author

Who runs the XFMS — Model Source MCP server?

xpansion.dev

Homepage More servers from xpansion.dev →

Own this server? Claim the listing →

Server facts

The XFMS — Model Source MCP server at a glance

Endpointhttps://xfms.vercel.app/mcp/

Operated byXFMS — Model Source (xpansion.dev)

CategoryDocs & AI

Sign-inNone — public data only

Available in gateYes — one-click connect

Works withClaude, ChatGPT, Cursor & any MCP client

FAQ

Questions, answered

Is there an official XFMS — Model Source MCP server?

Yes — XFMS — Model Source operates its own remote MCP server at xfms.vercel.app. gate connects you to that official endpoint and adds security scanning, per-tool access rules, and an activity log on top.

How do I connect XFMS — Model Source to Claude or ChatGPT?

Add gate's gateway URL to your AI client once, then pick XFMS — Model Source in the directory. No account or sign-in is needed. From then on, XFMS — Model Source's tools are available in every client you've connected to gate.

Do I need to host anything?

No. XFMS — Model Source runs the server, and gate is fully managed. You just connect one URL — there's nothing to install, deploy, or maintain.

Is the XFMS — Model Source MCP server safe to connect?

It's the vendor's official endpoint, and gate scans its tools for prompt injection and hidden instructions before it goes live, re-checks it whenever it changes, and lets you allow, block, or require approval for every single tool.