XF Model Source MCP Server

by xpansion Your server? Claim it

answering

XF Model Source is answering right now. Last checked 9 min ago. It exposes 7 tools. Last commit 18 Oct 2026.

Find the right AI model for your job. Free discovery and ranking; tests on your own key.

Uptime history 91 days of history · worst day 9%

91 days agonow

71.8%

Uptime 24h

196 of 273 checks

Tools

read from the server

1191 ms

Response time

average over 24h

Stars

last commit 18 Oct 2026

What changed 21

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 22 September 2026. No other catalogue keeps this.

21 Oct 2 tools changed the parameters they ask for benchmark, watch_job

21 Oct a tool description was rewritten watch_job

17 Oct 2 tools changed the parameters they ask for benchmark, compare

17 Oct a tool appeared watch_job

15 Oct 5 tools changed the parameters they ask for6 times that day benchmark, compare, discover and 2 more

15 Oct 5 tool descriptions were rewritten benchmark, compare, discover and 2 more

15 Oct a tool appeared field_results

22 Sep 3 tools changed the parameters they ask for benchmark, compare, rank

and 1 more, back to 22 September 2026

XF Model Source does not always answer

Over the last week it answered 72.5% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add xfms --transport http https://xfms.xpansion.dev/mcp/

Settings → Connectors → Add custom connector, then paste this address

https://xfms.xpansion.dev/mcp/

~/.codex/config.toml

[mcp_servers.xfms]
url = "https://xfms.xpansion.dev/mcp/"

.cursor/mcp.json

{
  "mcpServers": {
    "xfms": {
      "url": "https://xfms.xpansion.dev/mcp/"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "xfms": {
      "type": "http",
      "url": "https://xfms.xpansion.dev/mcp/"
    }
  }
}

This server publishes 2 more addresses. The block above uses the one we reach during checks; the full list is under Endpoints below, and the author may intend a particular one for your client.

Available tools 7

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

benchmark

benchmark

The live test: the 5 proven models and 1 promising newcomer from discovery do the person's real tasks side by side, every requirement is judged, and the results pick the winner. First call (session + tasks) returns the estimate and an offer — nothing is spent. Show the person the cost; only when they agree, call again with offer and go=true. Runs on the person's OpenRouter key (X-OpenRouter-Key header). Save the returned report as a local file.

compare

compare

Same live test as benchmark, but on the models the person names (model_ids). Needs a finished discover session so every requirement is judged. Estimate first, then go=true.

discover

discover

Discovery: finds the true requirements of the person's job before any model is chosen. Start with purpose: the reply carries the discovery instructions and the evidence catalogue. YOU ask the person the questions (one thing each, plain words, offering the returned choices); then call again with the sealed session, their answers and your structured updates. Each reply gives progress, rejected updates with reasons, next targets, answer choices from live data and a shortlist. At most 5 rounds. Ends with a confirmation view; call with confirm=true once the person agrees. The person can stop any time (end_now=true). Nothing about the person is stored by XFMS.

field

field_results

Results from real comparisons on Model Source for one kind of job (call with no job_type for the list): which models passed, how often, which won, typical cost per task and the most common failure. Counted without anyone's job details. A starting point; test on the person's own work before choosing.

pick

pick

The single best proven model for a job worked out with discover, with why and the runners-up. Pass the discover session.

rank

rank

The full shortlist for a job worked out with discover: 5 proven models and 1 promising newcomer, each with its standing on every requirement, plus near misses and what would change the order. Pass the discover session.

watch

watch_job

Saves a finished job for XF Model Watch, which re-tests it as new models arrive and emails the person only when a model passes every must-have and ranks higher on their priorities. Needs a signed-in subscriber. Ask the person first: Model Watch keeps the job and its example tasks (encrypted, deletable any time). Pass consent=true only if they agree. Pass the discover session, and either test_session from a finished comparison or the tasks, plus the model they use now. The first check runs as soon as the job is saved. To re-check a job the person already watches, pass check_now with the job's id or title instead (once a day per job; the result is emailed and shown at /account).

Endpoints

URL	Transport	State	Latency	Checked
https://xfms.vercel.app/mcp/	streamable-http	answering	68 ms	11 min ago
https://xfms.xpansion.dev/mcp/	streamable-http	answering	376 ms	9 min ago
https://xfms.xpansion.dev/mcp	streamable-http	answering	361 ms	9 min ago

Alternatives to XF Model Source

same job, measured the same way

Spring Prompt

by springprompt

The best prompt and the best model for the job, tested and improved by your coding agent.

12 tools answering

Index9

by index9-org

Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor

89 installs/wk local only

ParlayAPI

by jacobiusmakes

Sports odds, player props and source coverage for AI assistants. Connect with your own API key.

207 installs/wk 22 tools answering

Model Finder

by indigloo

Find the cheapest AI model that passes your tests: audit repo models, build evals, routing, sizing

859 installs/wk local only

Testfinder

by cloudcorprecords

Find the tests relevant to a source file from an import map, ranked, with the run command.

289 installs/wk local only

Endform

by endform

Find failing, flaky, and slow Playwright tests on Endform and keep your suite healthy as it grows.

33 662 installs/wk local only

TestOptim

by testoptim-ai

Run AI QA test runs on your web app and read the bugs they find, with steps to reproduce.

answering

iGods GEO Visibility Tool (GVT)

by igods

GEO visibility tests, score trends, sitemap discovery, and domain monitoring for AI agents.

19 tools answering

XF Model Source — questions

Answers built from our own checks of this server.

What can XF Model Source do?

It exposes 7 tools, read directly from the server on our last check. Among them: benchmark, compare, discover, field_results, pick, rank and 1 more. 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 XF Model Source working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 196 of 273 checks got a reply (71.8%), average response time 1191 ms. The bar chart above shows every period we have measured.

How do I connect XF Model Source?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does XF Model Source need an API key?

No. XF Model Source completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 7 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is XF Model Source?

It answers our handshake in 1191 ms on average, which is faster than 2% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is XF Model Source open source?

The code is open source: it is published under the MIT licence, written in Python, 0 stars on GitHub and 6 open issues. The licence covers the code in the repository, not the hosted service at xfms.vercel.app, which runs on its operator's own terms.