# XF Model Source

- Registry name: `dev.xpansion/xfms` · version 0.5.3
- Categories (automatic, keyword rules): Email & messaging, Productivity
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): experimental, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=dev.xpansion%2Fxfms
- Server page: https://mcpstation.net/s/dev.xpansion--xfms.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://xfms.xpansion.dev/mcp`

## Tools (as reported by the server, not verified)

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

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html