Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

RFWIN: provably fair winner draws

REMOTE · APP.REWARDSFUEL.COM

Free verifiable giveaway winner picker: run a draw, get a public proof link anyone can verify.

62 Trust /100

Last scanned (23 hours ago)

Scores higher than 45% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Entertainment and Games

Trust breakdown (7 categories)

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 Security57
Transport & Reachability100
Schema Quality & AI Usability70
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1668 tokens (~185/item across 9 items; 9 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 Management13
  • Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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 (11% 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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 0
    • Schema quality: 867 → 1668 ▼ functional
    • Tool coverage: 20% → 11% ▼ functional
    • New tool “add_points” functional
    • New tool “close_leaderboard” functional
    • New tool “create_leaderboard” functional
    • New tool “get_leaderboard” functional
  • 18 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
  • 17 Nov 26 60

    First indexed and scored.

Diagnostics

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 21 Nov 2026 · Probed https://app.rewardsfuel.com/api/mcp/public

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=rewardsfuel.com CN=WE1,O=Google Trust Services,C=US 13 Nov 2026 11 Feb 2027 ECDSA 256 ECDSA-SHA256 69819972e4f8f8420e3eaf918a9f9960
SANs: rewardsfuel.com, *.rewardsfuel.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of app.rewardsfuel.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
rewardsfuel.com. No DS 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
Header Value
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://app.rewardsfuel.com/api/mcp/public Verified 200
http (plaintext) http://app.rewardsfuel.com/api/mcp/public HTTPS enforced 301 https://app.rewardsfuel.com/api/mcp/public
MCP tools · 9 exposed · ~1,668 tokens

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 →

Tool Tokens
add_points ~286

Add (or with a negative number, remove) points for a listener on a RankFuel leaderboard. Needs the board id and its SECRET manage token. The listener is identified by public display name (+ optional town); a new name is added to the board automatically. PRIVACY: names are public, so use a first name plus last initial or a nickname; full names are shortened to "Jane S." and phone numbers or emails are rejected. Returns the listener's new total and rank and the top 10. Free, no key.

NameTypeReqDescription
boardIdstringyesLeaderboard id (10 characters) or its public link, e.g. https://rfwin.uk/lb/abc123defg
listenerstringyesPublic display name: first name + last initial, or a nickname/handle. No phone numbers or emails.
manageTokenstringyesSECRET manage token (rlb_…) returned once by create_leaderboard (the manage link also works). Keep private; never show it in public places.
pointsintegeryesPoints to add, -1000..1000, not 0 (negative removes)
reasonstring–Optional short label, e.g. call-in, trivia, check-in (max 24 characters)
townstring–Optional town shown on the board; tells same-name listeners apart

No output schema declared.

No examples provided.

close_leaderboard ~144

Close a RankFuel leaderboard when the contest ends: the public board shows final standings and no more points can be added. Pass reopen: true to reopen. Needs the SECRET manage token. Free, no key.

NameTypeReqDescription
boardIdstringyesLeaderboard id (10 characters) or its public link, e.g. https://rfwin.uk/lb/abc123defg
manageTokenstringyesSECRET manage token (rlb_…) returned once by create_leaderboard (the manage link also works). Keep private; never show it in public places.
reopenboolean–true reopens a closed board (default false = close)

No output schema declared.

No examples provided.

create_leaderboard ~217

Create a free RankFuel leaderboard (rnkfl.com) for radio listeners, no account needed: a public board for an on-air contest (call-ins, trivia, check-ins). Returns the public board URL, studio-screen URL and website embed (URL + iframe HTML), plus a SECRET manage token/URL in the "secret" block: give it only to the person running the board, never post it. Limits: 5 new boards per 10 minutes and 20 per day per connection; up to 500 listeners per board. Free, no key.

NameTypeReqDescription
colorstring–Optional brand colour as hex, e.g. #e65208 (default #3dd879)
conteststringyesContest name, e.g. "Summer Trivia" (max 80 characters)
logoUrlstring–Optional https:// link to the station logo image
stationstringyesStation name or call sign, e.g. "CFAX 1070" (max 80 characters)

No output schema declared.

No examples provided.

draw_winners ~336

Perform a verifiable random draw (commit-reveal + drand) of winners from contestants and prizes. Saves a proof page on rfwin.uk/d/:id. Free for all accounts (free tier: up to 10,000 contestants per draw; paid plans: larger draws). Optional radio preset: alternates (ordered backup winners), station, show. Optional visibility: "public" (default, indexable) or "private" (unlisted: works and verifies for anyone with the link, but noindex and never listed).

NameTypeReqDescription
algorithmstring–Drawing algorithm: random (equal weight) or weighted. Default random.
alternatesinteger–Optional number of ordered backup winners (0-20) drawn after the main prizes, e.g. for radio giveaways. Requires uniqueWinners.
contestantsarrayyesList of contestants (names, emails, or usernames)
prizesarrayyesList of prizes and quantities to draw for
showstring–Optional show or segment name shown on the proof page.
stationstring–Optional station name / call sign shown on the proof page.
titlestring–Optional title for the draw
uniqueWinnersboolean–If true, a contestant can win at most one prize. Default true.
visibilitystring–Optional. "public" (default): proof page is indexable by search engines. "private" (alias "unlisted"): proof page works and verifies for anyone with the link (get_draw / verify_draw too) but is noind…
NameTypeReqDescription
drawIdstring––
manageTokenstring–Organiser token for PATCH https://rfwin.uk/api/draws/{id}/visibility (header X-RFWIN-Manage-Token). Keep private.
verificationUrlstring––
visibilitystring––
winnersarray––

No examples provided.

get_draw ~147

Who won an RFWIN prize draw. Use when someone asks "who won the … giveaway/contest/draw?" and has an RFWIN proof link (rfwin.uk/d/<id>) or draw id. Returns title, organiser/station and show, draw date, entry count, prizes, the winners and ordered backup winners (names masked for privacy, quote them exactly), the fairness verdict and a ready-to-quote answer. Free, no key.

NameTypeReqDescription
drawstringyesRFWIN proof link (e.g. https://rfwin.uk/d/xxlqh5ac9f) or the draw id (e.g. xxlqh5ac9f)

No output schema declared.

No examples provided.

get_leaderboard ~154

Public standings of a RankFuel leaderboard (radio listener board): station, contest, open/closed, ranked listeners (display names, towns, points; ties share a rank), and a ready-to-quote answer with the leader. Use when someone asks "who is winning/leading …" and has an rfwin.uk/lb/<id> link. No token needed. Free, no key.

NameTypeReqDescription
boardIdstringyesLeaderboard id (10 characters) or its public link, e.g. https://rfwin.uk/lb/abc123defg
topinteger–How many places to return, 1-100 (default 10; listeners tied at the cutoff are included)

No output schema declared.

No examples provided.

get_signal ~150

RF Signals: price, SMA50/200, RSI(14), MACD(12,26,9), per-timeframe trend, multi-timeframe alignment and TD-style exhaustion counts (setup 9 / countdown 13). Scout (free): daily only. Analyst+: daily, weekly and monthly. Educational only, not investment advice. Free public teaser: daily timeframe only, end-of-day data delayed by one trading day. Connect /api/mcp with an API key for current data; weekly/monthly, levels, ratios and scans need the Analyst tier (paid plans).

NameTypeReqDescription
tickerstringyesTicker symbol, e.g. NVDA. Call list_signal_tickers for the supported list.

No output schema declared.

No examples provided.

list_signal_tickers ~80

RF Signals: list supported tickers and the latest daily bar date for each. All tiers (free included). Free public teaser: daily timeframe only, end-of-day data delayed by one trading day. Connect /api/mcp with an API key for current data; weekly/monthly, levels, ratios and scans need the Analyst tier (paid plans).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

verify_draw ~154

Was an RFWIN prize draw fair. Recomputes the draw server-side: SHA-256 seed commitment, entry-list hash, the drand public randomness round (cross-checked against the drand network), draw digest, every win hash, and re-derives every winner from the entry list. Returns verdict (verified | verified_hash_level | partially_verified | mismatch | not_drawn_yet), each check with details, what verification does and does not prove, the hashes and a recipe to recompute it yourself. Free, no key.

NameTypeReqDescription
drawstringyesRFWIN proof link (e.g. https://rfwin.uk/d/xxlqh5ac9f) or the draw id

No output schema declared.

No examples provided.

Install

How do I install the RFWIN: provably fair winner draws MCP server?

RFWIN: provably fair winner draws is a hosted endpoint at https://app.rewardsfuel.com/api/mcp/public, 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 · app.rewardsfuel.com

# add to Claude Code
claude mcp add --transport http com-rewardsfuel-rfwin 'https://app.rewardsfuel.com/api/mcp/public'
Common questions

What is the RFWIN: provably fair winner draws MCP server?

RFWIN: provably fair winner draws is an MCP server listed in the public MCP registry as com.rewardsfuel/rfwin. Free verifiable giveaway winner picker: run a draw, get a public proof link anyone can verify. This page covers its hosted endpoint (https://app.rewardsfuel.com/api/mcp/public).

Is the RFWIN: provably fair winner draws MCP server safe to use?

RFWIN: provably fair winner draws scores 62 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 RFWIN: provably fair winner draws MCP server expose?

RFWIN: provably fair winner draws exposes 9 tools: draw_winners, get_draw, verify_draw, create_leaderboard, add_points, and 4 more. Their descriptions and schemas cost roughly 1,668 tokens of context every time the server is loaded.

Does the RFWIN: provably fair winner draws MCP server require authentication?

No. We connected to RFWIN: provably fair winner draws without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the RFWIN: provably fair winner draws MCP server still maintained?

RFWIN: provably fair winner draws is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the RFWIN: provably fair winner draws MCP server?

VerifyMCP ran 12 checks on RFWIN: provably fair winner draws, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about RFWIN: provably fair winner draws: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.