mcpbeat

XFMS — Model Source MCP Server

dev.xpansion/xfms
not responding

XFMS — Model Source is listed as active in the registry but did not answer our last check. It exposes 5 tools. Last commit 24 May 2026.

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

Uptime history 39 hours of history · worst hour 0%
39 hours agonow
93.4%
Uptime 24h
85 of 91 checks
5
Tools
read from the server
333 ms
Response time
average over 24h
0
Stars
last commit 24 May 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 15 min ago.

run in your terminal
claude mcp add xfms --transport http https://xfms.vercel.app/mcp/
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "xfms": {
      "url": "https://xfms.vercel.app/mcp/"
    }
  }
}
~/.codex/config.toml
[mcp_servers.xfms]
url = "https://xfms.vercel.app/mcp/"
.cursor/mcp.json
{
  "mcpServers": {
    "xfms": {
      "url": "https://xfms.vercel.app/mcp/"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "xfms": {
      "url": "https://xfms.vercel.app/mcp/"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

benchmark
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 if results are too close to call), runs them through the picked models in parallel, and returns real cost, latency, and plain-English commentary on who won what. Use AFTER `pick` or `rank` when the user wants the engine's own picks stress-tested with live data. DO NOT use this when the user has already named specific candidate models — the engine will ignore the names and test its own picks. Use `compare` instead in that case. Costs more than `rank` (15+ live LLM calls).
compare
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, runs them through every named model in parallel, and returns real cost, latency, and plain-English commentary on who won what. Unknown IDs are dropped with a note; if fewer than 2 IDs resolve, the call refuses. Use this whenever the user names specific models to compare (e.g. 'A/B test X and Y'). For engine-chosen candidates, use `benchmark` instead. Costs more than `rank` (10+ live LLM calls). Free-tier note: when any candidate ends in ':free', the probe is capped at 3 queries (no adaptive expansion) because free-tier rate limits often push longer probes past the deploy's 5-minute ceiling — evidence will be shallower. The commentary surfaces this when it happens.
discover
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 purpose before committing to a pick.
pick
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.
rank
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.

Endpoints

URLTransportStateLatencyChecked
https://xfms.vercel.app/mcp/ streamable-http answering 46 ms 15 min ago

XFMS — Model Source — questions

Answers built from our own checks of this server.

What can XFMS — Model Source do?
It exposes 5 tools, read directly from the server on our last check. Among them: benchmark, compare, discover, pick, rank. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is XFMS — Model Source working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 85 of 91 checks got a reply (93.4%), average response time 333 ms. The bar chart above shows every period we have measured.
The registry lists XFMS — Model Source as active — why does it not respond?
The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.
How do I connect XFMS — Model Source?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does XFMS — Model Source need an API key?
No. XFMS — Model Source completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is XFMS — Model Source?
It answers our handshake in 333 ms on average, which is faster than 42% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is XFMS — Model Source open source?
Yes — it is published under the MIT licence, written in Python, 0 stars on GitHub and 4 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.