XF Model Source

Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.

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

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "XF Model Source": {
      "url": "https://xfms.xpansion.dev/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (7)

• rank read-only

  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.

  Parameters:

  • session (required) — string — The sealed session from a discover conversation. Ranking is built from what discovery found out about the job — call discover first.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• pick read-only

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

  Parameters:

  • session (required) — string — The sealed session from a discover conversation. Ranking is built from what discovery found out about the job — call discover first.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• discover read-only

  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.

  Parameters:

  • answers — object — The person's answers this round, keyed by the question you asked them (short key or the question text), in their exact words. For an XFMS question the person already answered earlier, send {"choice": choice id, "from_earlier": their exact earlier words} instead of asking it.
  • confirm — boolean — The person agrees with the confirmation view.
  • context — array — Optional, with the person's consent: short labelled excerpts (sample inputs, a conversation summary). Used for this request only, never kept.
  • end_now — boolean — The person wants to stop and see the best result so far.
  • purpose — string — The job the person wants an AI model for, in their own words. Needed to start.
  • session — string — The sealed session value from the previous discover response. Pass it back unchanged.
  • updates — object — What you learned from the answers, in the format the first discover reply's instructions give: conclusions, requirements, shapes, open_items, item_moves, relation, usage, survivors_matter, pushback. XFMS checks each against its rules and reports any it rejects.
  • corrections — array — Changes the person makes in the confirmation view: {requirement_id, field, value}.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• benchmark read-only

  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.

  Parameters:

  • session (required) — string — The sealed session from a finished discover conversation.
  • go — boolean — The person approved the estimate. Spends on their key.
  • offer — string — The offer from the estimate. Pass it with go=true to run.
  • tasks — array — The person's real work to test on, real examples first. Write extra tasks yourself only for the gaps XFMS names, with source 'made up'. Images as data URLs.
  • ratings — object — Blind ratings: {task id: {letter: good|ok|poor}}, with test_session.
  • overruled — array — Failures the person accepts, as 'model id|requirement words'.
  • jobs_wanted — integer — How many AI jobs the person would want watched, if they said; sizes the Model Watch plan.
  • test_session — string — From a finished run, to overrule failures without rerunning.
  • current_model — string — OpenRouter id of the model the job uses now, if any.
  • runs_per_month — number — Roughly how many times a month the job runs, if known.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• field_results read-only

  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.

  Parameters:

  • job_type — string — One key from the list returned when called without it.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• 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).

  Parameters:

  • tasks — array — Example tasks, if no test_session.
  • title — string — A short name for the job, in the person's words.
  • consent — boolean — The person agreed to Model Watch keeping this job.
  • session — string — The discover session.
  • check_now — ['integer', 'string'] — Check a job they already watch now: its id or title. Leave out when saving a job.
  • test_session — string — From a finished comparison; carries its tasks.
  • current_model — string — OpenRouter id of the model the job uses now.
  • runs_per_month — number — Roughly how many times a month the job runs, if known.

  Hints: read-only no · destructive no · idempotent no · open-world no

• compare read-only

  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.

  Parameters:

  • session (required) — string — The sealed session from a finished discover conversation.
  • go — boolean — The person approved the estimate. Spends on their key.
  • offer — string — The offer from the estimate. Pass it with go=true to run.
  • tasks — array — The person's real work to test on, real examples first. Write extra tasks yourself only for the gaps XFMS names, with source 'made up'. Images as data URLs.
  • ratings — object — Blind ratings: {task id: {letter: good|ok|poor}}, with test_session.
  • model_ids — array — The OpenRouter ids of the models the person named.
  • overruled — array — Failures the person accepts, as 'model id|requirement words'.
  • test_session — string — From a finished run, to overrule failures without rerunning.
  • current_model — string — OpenRouter id of the model the job uses now, if any.
  • runs_per_month — number — Roughly how many times a month the job runs, if known.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.