XF Model Source
REMOTE · XFMS.XPANSION.DEV
Find the right AI model for your job. Free discovery and ranking; tests on your own key.
Available components
Last scanned (10 hours ago)
Scores higher than 66% of remote servers
Reachable. Last reached 5 Nov 2026.
Category AI and Machine Learning
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. How we score → Why this is hard to score →
Endpoint Security74
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability60
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1532 tokens (~218/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management57
- Stability check failed: schema churn in the 30 days we've observed: 0 tool removals, 4 breaking changes, 0 auth/transport breaks, 2 additions. See how to fix → Fail
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (71% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 23 Oct 26 −1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 57.
- 22 Oct 26 0
- Tool “watch_job” rewrote its description, which is the text the model reads security
- “watch_job” added an optional parameter “check_now” cosmetic
- “benchmark” added an optional parameter “jobs_wanted” cosmetic
- “watch_job” made “session” optional cosmetic
- “watch_job” made “consent” optional cosmetic
- 17 Oct 26 −2
- HSTS header: pass → fail ▼ security
- Tool “watch_job” rewrote its description, which is the text the model reads security
- “watch_job” reworded the description of “consent” cosmetic
- 16 Oct 26 0
- Schema quality: 999 → 1424 ▼ functional
- Tool coverage: 100% → 71% ▼ functional
- New tool “field_results” functional
- New tool “watch_job” functional
- “compare” added an optional parameter “runs_per_month” cosmetic
- “compare” added an optional parameter “current_model” cosmetic
- “benchmark” added an optional parameter “runs_per_month” cosmetic
- “benchmark” added an optional parameter “current_model” cosmetic
- “discover” reworded the description of “answers” cosmetic
- 15 Oct 26 −7
- Stability: pass → fail ▼ security
- A breaking change shipped without a version bump: still 1.30.0 ▼ security
- Tool “discover” rewrote its description, which is the text the model reads security
- Tool “pick” rewrote its description, which is the text the model reads security
- Tool “rank” rewrote its description, which is the text the model reads security
- Tool “benchmark” rewrote its description, which is the text the model reads security
- Tool “compare” rewrote its description, which is the text the model reads security
- “compare” added a required parameter “session”, so existing callers break ▼ functional
- “pick” added a required parameter “session”, so existing callers break ▼ functional
- “rank” added a required parameter “session”, so existing callers break ▼ functional
- “benchmark” added a required parameter “session”, so existing callers break ▼ functional
- “compare” dropped the required parameter “purpose” ▼ functional
- “pick” dropped the required parameter “purpose” ▼ functional
- “rank” dropped the required parameter “purpose” ▼ functional
- “benchmark” dropped the required parameter “purpose” ▼ functional
- Schema quality: 240 → 199 ▲ functional
- Schema quality: excellent → good functional
- “compare” added an optional parameter “go” cosmetic
- “compare” added an optional parameter “offer” cosmetic
- “compare” added an optional parameter “overruled” cosmetic
- “compare” added an optional parameter “ratings” cosmetic
- “compare” added an optional parameter “tasks” cosmetic
- “compare” added an optional parameter “test_session” cosmetic
- “discover” added an optional parameter “answers” cosmetic
- “discover” added an optional parameter “confirm” cosmetic
- “discover” added an optional parameter “context” cosmetic
- “discover” added an optional parameter “corrections” cosmetic
- “discover” added an optional parameter “end_now” cosmetic
- “discover” added an optional parameter “session” cosmetic
- “discover” added an optional parameter “updates” cosmetic
- “benchmark” added an optional parameter “go” cosmetic
- “benchmark” added an optional parameter “offer” cosmetic
- “benchmark” added an optional parameter “overruled” cosmetic
- “benchmark” added an optional parameter “ratings” cosmetic
- “benchmark” added an optional parameter “tasks” cosmetic
- “benchmark” added an optional parameter “test_session” cosmetic
- “compare” reworded the description of “model_ids” cosmetic
- “discover” reworded the description of “purpose” cosmetic
- “compare” dropped the optional parameter “primary” cosmetic
- “compare” dropped the optional parameter “test_queries” cosmetic
- “rank” dropped the optional parameter “primary” cosmetic
- “rank” dropped the optional parameter “top_n” cosmetic
- “rank” dropped the optional parameter “capabilities” cosmetic
- “benchmark” dropped the optional parameter “capabilities” cosmetic
- “benchmark” dropped the optional parameter “primary” cosmetic
- “benchmark” dropped the optional parameter “test_queries” cosmetic
- “benchmark” dropped the optional parameter “top_n” cosmetic
- “compare” made “model_ids” optional cosmetic
- “discover” made “purpose” optional cosmetic
- Tool “compare” changed its title: Compare specific models head-to-head with real test queries → Test models the person named on their own work cosmetic
- Tool “discover” changed its title: Discover quality dimensions → Work out what the job really needs cosmetic
- Tool “pick” changed its title: Pick the best LLM → Pick the best model for a discovered job cosmetic
- Tool “rank” changed its title: Rank LLMs → Rank models for a discovered job cosmetic
- Tool “benchmark” changed its title: Benchmark the engine's top picks with real test queries → Test the shortlist on the person's own work cosmetic
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 23 Sept 26 0
- Schema quality: 209 → 240 ▼ functional
- Server version: 1.27.2 → 1.30.0 functional
- “benchmark” added an optional parameter “capabilities” cosmetic
- “benchmark” added an optional parameter “primary” cosmetic
- “benchmark” added an optional parameter “test_queries” cosmetic
- “compare” added an optional parameter “test_queries” cosmetic
- “benchmark” added an optional parameter “top_n” cosmetic
- “compare” reworded the description of “primary” cosmetic
- “rank” reworded the description of “primary” cosmetic
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://xfms.xpansion.dev/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=xfms.xpansion.dev | CN=YE2,O=Let's Encrypt,C=US | 20 Sept 2026 | 19 Dec 2026 | ECDSA 256 | ECDSA-SHA384 | 59162516933894d4e8e8267005034c09153 |
| SANs: xfms.xpansion.dev | ||||||
| CN=YE2,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 4df3b15dd6c0784c507cd37b58e6f115 |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of xfms.xpansion.dev. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | present | 60074 | 8 | Verified |
| xpansion.dev. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://xfms.xpansion.dev/mcp | Verified | 200 | |
| http (plaintext) | http://xfms.xpansion.dev/mcp | HTTPS enforced | 301 | https://xfms.xpansion.dev/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
benchmark Test the shortlist on the person's own work ~339
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.
| Name | Type | Req | Description |
|---|---|---|---|
| current_model | string | – | OpenRouter id of the model the job uses now, if any. |
| go | boolean | – | The person approved the estimate. Spends on their key. |
| jobs_wanted | integer | – | How many AI jobs the person would want watched, if they said; sizes the Model Watch plan. |
| offer | string | – | The offer from the estimate. Pass it with go=true to run. |
| overruled | array | – | Failures the person accepts, as 'model id|requirement words'. |
| ratings | object | – | Blind ratings: {task id: {letter: good|ok|poor}}, with test_session. |
| runs_per_month | number | – | Roughly how many times a month the job runs, if known. |
| session | string | yes | The sealed session from a finished discover conversation. |
| 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. |
| test_session | string | – | From a finished run, to overrule failures without rerunning. |
Structured output declared, but exposes no named fields.
No examples provided.
compare Test models the person named on their own work ~266
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.
| Name | Type | Req | Description |
|---|---|---|---|
| current_model | string | – | OpenRouter id of the model the job uses now, if any. |
| go | boolean | – | The person approved the estimate. Spends on their key. |
| model_ids | array | – | The OpenRouter ids of the models the person named. |
| offer | string | – | The offer from the estimate. Pass it with go=true to run. |
| overruled | array | – | Failures the person accepts, as 'model id|requirement words'. |
| ratings | object | – | Blind ratings: {task id: {letter: good|ok|poor}}, with test_session. |
| runs_per_month | number | – | Roughly how many times a month the job runs, if known. |
| session | string | yes | The sealed session from a finished discover conversation. |
| 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. |
| test_session | string | – | From a finished run, to overrule failures without rerunning. |
Structured output declared, but exposes no named fields.
No examples provided.
discover Work out what the job really needs ~399
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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":… |
| 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. |
| corrections | array | – | Changes the person makes in the confirmation view: {requirement_id, field, value}. |
| 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.… |
Structured output declared, but exposes no named fields.
No examples provided.
field_results What has worked for jobs like this ~89
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.
| Name | Type | Req | Description |
|---|---|---|---|
| job_type | string | – | One key from the list returned when called without it. |
No output schema declared.
No examples provided.
pick Pick the best model for a discovered job ~62
The single best proven model for a job worked out with discover, with why and the runners-up. Pass the discover session.
| Name | Type | Req | Description |
|---|---|---|---|
| session | string | yes | The sealed session from a discover conversation. Ranking is built from what discovery found out about the job — call discover first. |
Structured output declared, but exposes no named fields.
No examples provided.
rank Rank models for a discovered job ~81
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.
| Name | Type | Req | Description |
|---|---|---|---|
| session | string | yes | The sealed session from a discover conversation. Ranking is built from what discovery found out about the job — call discover first. |
Structured output declared, but exposes no named fields.
No examples provided.
watch_job Watch this job (XF Model Watch subscribers) ~296
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).
| Name | Type | Req | Description |
|---|---|---|---|
| check_now | integer|string | – | Check a job they already watch now: its id or title. Leave out when saving a job. |
| consent | boolean | – | The person agreed to Model Watch keeping this job. |
| 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. |
| session | string | – | The discover session. |
| tasks | array | – | Example tasks, if no test_session. |
| test_session | string | – | From a finished comparison; carries its tasks. |
| title | string | – | A short name for the job, in the person's words. |
No output schema declared.
No examples provided.
How do I install the XF Model Source MCP server?
XF Model Source is a hosted endpoint at https://xfms.xpansion.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · xfms.xpansion.dev
claude mcp add --transport http dev-xpansion-xfms 'https://xfms.xpansion.dev/mcp'
What is the XF Model Source MCP server?
XF Model Source is an MCP server listed in the public MCP registry as dev.xpansion/xfms. Find the right AI model for your job. Free discovery and ranking; tests on your own key. This page covers its hosted endpoint (https://xfms.xpansion.dev/mcp).
Is the XF Model Source MCP server safe to use?
XF Model Source scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the XF Model Source MCP server expose?
XF Model Source exposes 7 tools: rank, pick, discover, benchmark, field_results, and 2 more. Their descriptions and schemas cost roughly 1,532 tokens of context every time the server is loaded.
Does the XF Model Source MCP server require authentication?
No. We connected to XF Model Source without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the XF Model Source MCP server still maintained?
XF Model Source is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.