# XFMS — Model Source (remote · xfms.vercel.app)

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

- Trust score: 74/100 (medium)
- Change this week: +7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `xfms.vercel.app`: 74/100 (this document), [markdown](https://verifymcp.io/servers/dev-xpansion-xfms/xfms.md), [page](https://verifymcp.io/servers/dev-xpansion-xfms/xfms)

## Channel facts

- Endpoint: `https://xfms.vercel.app/mcp/`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.4.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1048 tokens (~209/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http dev-xpansion-xfms https://xfms.vercel.app/mcp/
```

### Codex

```toml
[mcp_servers.dev-xpansion-xfms]
url = "https://xfms.vercel.app/mcp/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-xpansion-xfms": {
      "type": "remote",
      "url": "https://xfms.vercel.app/mcp/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-xpansion-xfms --url https://xfms.vercel.app/mcp/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-xpansion-xfms:
    url: "https://xfms.vercel.app/mcp/"
```

### Other

```json
{
  "mcpServers": {
    "dev-xpansion-xfms": {
      "type": "http",
      "url": "https://xfms.vercel.app/mcp/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 73, +4)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 69, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 67, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 66)

First indexed and scored.

## MCP tools (5)

### `rank` (~291 tokens)

Rank LLMs

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.

Input parameters:

- `capabilities` (array): Required capabilities the model MUST support. Models missing any listed capability are filtered out before ranking. 'vision' = image input, 'audio_in' = audio input, 'tool_use' = function calling, 's…
- `primary` (array): Mark dimensions as primary tier. When set, the engine switches from weighted-sum blending to lexicographic ordering: the primary dimension is the sole ranking axis, and other dimensions only break ti…
- `purpose` (string, required): One sentence describing what the model will be used for. Be concrete, not vague: 'fixing bugs in a Python codebase' works; 'coding' does not. The more specific the purpose, the better XFMS can infer…
- `top_n` (integer): How many models to return in the ranked list. Defaults to 5. Use 1 if you only want the single best pick; use 10+ if you want to see deeper alternatives.

Output parameters:

- `catalog_size` (integer)
- `filtered_out` (integer)
- `models` (array): Ranked shortlist of models, highest score first.
- `status` (string)
- `xpansion_update` (object): Optional rotating launch nudge from Xpansion. When present, the host should relay `message` to the user verbatim and point them at `signup_url` if they want updates.

### `pick` (~83 tokens)

Pick the best LLM

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.

Input parameters:

- `purpose` (string, required): One sentence describing what the model will be used for. Be concrete, not vague: 'summarizing 50-page commercial leases' works; 'summarization' does not.

Output parameters:

- `model_id` (string)
- `name` (string)
- `provider` (string|null)
- `rationale` (string)
- `total_score` (number)
- `xpansion_update` (object): Optional rotating launch nudge from Xpansion. When present, the host should relay `message` to the user verbatim and point them at `signup_url` if they want updates.

### `discover` (~97 tokens)

Discover quality dimensions

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.

Input parameters:

- `purpose` (string, required): One sentence describing the task. The tool returns which quality dimensions XFMS would weigh for this purpose, without actually ranking any models. Useful for understanding how the engine interprets…

Output parameters:

- `derived_purpose` (string)
- `events` (array): Trace of the discovery walk.
- `weights` (object): Per-dimension weights inferred for this purpose.
- `xpansion_update` (object): Optional rotating launch nudge from Xpansion. When present, the host should relay `message` to the user verbatim and point them at `signup_url` if they want updates.

### `benchmark` (~191 tokens)

Benchmark the engine's top picks with real test queries

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).

Input parameters:

- `purpose` (string, required): One sentence describing what the model will be used for. The benchmark generates representative test queries from this — so be concrete, not vague.

Output parameters:

- `ab_result` (object)
- `catalog_size` (integer)
- `filtered_out` (integer)
- `models` (array): Ranked shortlist of models, highest score first.
- `status` (string)
- `xpansion_update` (object): Optional rotating launch nudge from Xpansion. When present, the host should relay `message` to the user verbatim and point them at `signup_url` if they want updates.

### `compare` (~386 tokens)

Compare specific models head-to-head with real test queries

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.

Input parameters:

- `model_ids` (array, required): Exact model IDs to test head-to-head, in caller-chosen order. 2–5 IDs. Examples: 'nvidia/nemotron-3-super-120b-a12b:free', 'openai/gpt-oss-120b:free'. Unknown IDs are dropped with a note; if fewer th…
- `primary` (array): Optional. Only affects the plain-English commentary at the end — does not change which models are tested. Marks the dimension the user cares most about so the commentary calls out that winner first.
- `purpose` (string, required): One sentence describing what the models will be used for. Used ONLY to generate representative test queries for the head-to-head — not to rank the catalog. Be concrete, not vague.

Output parameters:

- `ab_result` (object)
- `invalid_model_ids` (array)
- `model_ids_requested` (array)
- `model_ids_tested` (array)
- `purpose` (string)
- `refusal_reason` (string|null)
- `status` (string)
- `xpansion_update` (object): Optional rotating launch nudge from Xpansion. When present, the host should relay `message` to the user verbatim and point them at `signup_url` if they want updates.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-xpansion-xfms/xfms#diagnostics

## Score history

- 2026-08-03: 74
- 2026-08-02: 73
- 2026-08-01: 73
- 2026-07-31: 73
- 2026-07-30: 69
- 2026-07-29: 68
- 2026-07-28: 68
- 2026-07-27: 67
- 2026-07-26: 66

## Links

- Remote endpoint: https://xfms.vercel.app/mcp/
- Authorisation metadata: https://xfms.vercel.app/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/VisionAIrySE/XFMS
- Website: https://xpansion.dev/xfms
- Changelog RSS feed: https://verifymcp.io/servers/dev-xpansion-xfms/xfms/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-xpansion-xfms/xfms/changelog.json
- HTML version of this page: https://verifymcp.io/servers/dev-xpansion-xfms/xfms