Neural network swarm orchestration with WebAssembly acceleration and MCP integration
Nothing to run from here
XFMS — Model Source is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
7
tools declared
remote
at its publisher
—
calls last 7d
What it does
Find the right AI model for your job. Free discovery and ranking; tests on your own key.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http xfms-model-source-mcp https://xfms.xpansion.dev/mcp
# 2 — ask your agent for something these tools do
# rank, pick, discover and 4 more
XFMS — Model Source costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
XPAll 1 server
xpansion1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http xfms-model-source-mcp https://xfms.xpansion.dev/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — some of its tools take a key of its publisher’s own, and the rest work without.
What it asks of you
Nothing is required, but it can take X-OpenRouter-Key header (Your OpenRouter API key. Required only for the compare and benchmark tools (they run live test queries against the named models on OpenRouter — that cost rides with you, not us). The rank, pick, and discover tools work without it. Get a key at https://openrouter.ai/keys.) if you want to set it. Its publisher says some of its tools need it, and the rest work without.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
7 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session | string | yes | The sealed session from a discover conversation. Ranking is built from what discovery found out about the job — call discover first. |
The single best proven model for a job worked out with discover, with why and the runners-up. Pass the discover session.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session | string | yes | The sealed session from a discover conversation. Ranking is built from what discovery found out about the job — call discover first. |
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 updat
| Parameter | Type | Required | Notes |
|---|---|---|---|
| purpose | string | no | The job the person wants an AI model for, in their own words. Needed to start. |
| context | array | no | Optional, with the person's consent: short labelled excerpts (sample inputs, a conversation summary). Used for this request only, never kept. |
| session | string | no | The sealed session value from the previous discover response. Pass it back unchanged. |
| answers | object | no | 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": |
| updates | object | no | 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. X |
| corrections | array | no | Changes the person makes in the confirmation view: {requirement_id, field, value}. |
| confirm | boolean | no | The person agrees with the confirmation view. |
| end_now | boolean | no | The person wants to stop and see the best result so far. |
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 he
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session | string | yes | The sealed session from a finished discover conversation. |
| tasks | array | no | 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. |
| offer | string | no | The offer from the estimate. Pass it with go=true to run. |
| go | boolean | no | The person approved the estimate. Spends on their key. |
| test_session | string | no | From a finished run, to overrule failures without rerunning. |
| overruled | array | no | Failures the person accepts, as 'model id|requirement words'. |
| current_model | string | no | OpenRouter id of the model the job uses now, if any. |
| runs_per_month | number | no | Roughly how many times a month the job runs, if known. |
| ratings | object | no | Blind ratings: {task id: {letter: good|ok|poor}}, with test_session. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_type | string | no | One key from the list returned when called without it. |
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_sessi
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session | string | yes | The discover session. |
| test_session | string | no | From a finished comparison; carries its tasks. |
| tasks | array | no | Example tasks, if no test_session. |
| current_model | string | no | OpenRouter id of the model the job uses now. |
| title | string | no | A short name for the job, in the person's words. |
| runs_per_month | number | no | Roughly how many times a month the job runs, if known. |
| consent | boolean | yes | The person agreed to Model Watch keeping this job. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session | string | yes | The sealed session from a finished discover conversation. |
| tasks | array | no | 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. |
| offer | string | no | The offer from the estimate. Pass it with go=true to run. |
| go | boolean | no | The person approved the estimate. Spends on their key. |
| test_session | string | no | From a finished run, to overrule failures without rerunning. |
| overruled | array | no | Failures the person accepts, as 'model id|requirement words'. |
| current_model | string | no | OpenRouter id of the model the job uses now, if any. |
| runs_per_month | number | no | Roughly how many times a month the job runs, if known. |
| ratings | object | no | Blind ratings: {task id: {letter: good|ok|poor}}, with test_session. |
| model_ids | array | no | The OpenRouter ids of the models the person named. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install XFMS — Model Source or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 0.5.3 · scanned 20 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest1beb8aca8a39bff5a18732a0044062ff92812c523f2f24cdb56d5e4f97ff3034
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| rank | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| pick | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| discover | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| benchmark | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| field_results | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| watch_job | state-write | state-write: declares readOnlyHint: false |
| compare | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest1beb8aca8a39bff5
Scanned2026-10-20
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.5.3.
0.5.3
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish XFMS — Model Source can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.