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.

Saifuban

REMOTE · ZRPHNUVRSLDCYCXTDFTV.SUPABASE.CO

Hard daily caps on AI agents' API spend, plus phone approval before any other payment.

+3 this week 82 Trust /100

Last scanned (12 hours ago)

Scores higher than 81% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Finance and Payments

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 Security94
Transport & Reachability100
Schema Quality & AI Usability63
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 917 tokens (~229/item across 4 items; 4 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 Management43
  • Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage94
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 83% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 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
What we tested

Checks we ran (13)

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

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.

  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Nov 26 0
    • Server version: 0.7.1 → 0.8.0 functional
  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 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.

  • 10 Nov 26 +5
    • Authorization: partial → pass ▲ security
    • First check of Authorization: partial security
    • Tool “get_budget” rewrote its description, which is the text the model reads security
    • Tool “request_payment” rewrote its description, which is the text the model reads security
    • Schema quality: 202 → 229 ▼ functional
    • Server version: 0.5.0 → 0.7.1 functional
    • “request_payment” added an optional parameter “idempotency_key” cosmetic
  • 9 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “request_payment” rewrote its description, which is the text the model reads security
    • Schema quality: 167 → 202 ▼ functional
    • Tool coverage: 71% → 82% ▲ functional
    • Stability: unverified → 0.03 ▲ functional
    • Server version: 0.4.0 → 0.5.0 functional
    • New tool “list_payments” functional
    • “request_payment” added an optional parameter “recurring” cosmetic
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://zrphnuvrsldcycxtdftv.supabase.co/functions/v1/saifuban-mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=supabase.co CN=WE1,O=Google Trust Services,C=US 24 Oct 2026 22 Jan 2027 ECDSA 256 ECDSA-SHA256 d2b50611cd88e9c50e4e2231f4d3f059
SANs: supabase.co, *.supabase.co
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 zrphnuvrsldcycxtdftv.supabase.co. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
co. DS published 7786 8 Verified
supabase.co. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer resource_metadata="https://zrphnuvrsldcycxtdftv.supabase.co/functions/v1/saifuban-mcp/.well-known/oauth-protected-resource", scope="saifuban"

Bearer resource_metadata="https://zrphnuvrsldcycxtdftv.supabase.co/functions/v1/saifuban-mcp/.well-known/oauth-protected-resource", scope="saifuban"
Header Value
strict-transport-security max-age=31536000; includeSubDomains; preload

Protected resource metadata

Document https://zrphnuvrsldcycxtdftv.supabase.co/functions/v1/saifuban-mcp/.well-known/oauth-protected-resource
Retrieved Yes
Resource https://zrphnuvrsldcycxtdftv.supabase.co/functions/v1/saifuban-mcp
Authorisation server https://zrphnuvrsldcycxtdftv.supabase.co/functions/v1/saifuban-mcp

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://zrphnuvrsldcycxtdftv.supabase.co/functions/v1/saifuban-mcp Verified 200
http (plaintext) http://zrphnuvrsldcycxtdftv.supabase.co/functions/v1/saifuban-mcp HTTPS enforced 301 https://zrphnuvrsldcycxtdftv.supabase.co/functions/v1/saifuban-mcp
MCP tools · 4 exposed · ~840 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
check_payment_status ~68

以前の申請(request_id)が承認されたかを確認する。approved になってから支払うこと。 / Check whether an earlier request was approved. Pay only after it is approved.

NameTypeReqDescription
request_idintegeryes–
wait_secondsinteger––

No output schema declared.

No examples provided.

get_budget ~70

このAIが今日・今週・今月あといくら使えるか、1回の上限、自動承認ライン、使ってよい支払先を確認する。 / Check the remaining daily, weekly and monthly budget, per-payment limit, auto-approve amount and allowed merchants.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_payments ~168

このAI自身の過去の支払い申請を調べる(二重払い・二重契約を避けるため)。例: 今月すでにSpotifyを承認済みか。 / Look up this agent's own past payment requests, e.g. to check whether a Spotify charge was already approved this month, and avoid paying twice.

NameTypeReqDescription
daysinteger–何日前までさかのぼるか(既定30) / how many days back (default 30)
limitinteger–最大件数(既定20) / max results (default 20)
merchantstring–支払先の名前で絞り込む(部分一致) / filter by merchant name (partial match)

No output schema declared.

No examples provided.

request_payment ~534

お金を使う前に必ず呼ぶツール。支払先・金額・理由を財布番に申請し、許可が出たかを返す。status が approved のときだけ支払ってよい。pending_approval は持ち主の承認待ちで、まだ支払ってはいけない(持ち主のスマホに通知が届く)。denied や expired のときは支払わず、reason をユーザーに伝える。 / Call this BEFORE spending any money. Pay only when status is approved. pending_approval means the owner must approve on their phone — do not pay yet. When approved, the result includes payment_token: a single-use token that payment tools can verify, so payments made without approval can be refused. If the payment is a subscription or renews automatically, set recurring. Before buying something you may already have paid for, call list_payments. If you get pending_approval, poll check_payment_status instead of calling request_payment again (a repeat of a pending request returns the same request).

NameTypeReqDescription
amountnumberyes支払う金額(税込) / amount to pay, tax included
currencystring–amount の通貨。省略すると持ち主の通貨 / currency of amount; defaults to the owner's currency
idempotency_keystring–同じ支払いをやり直すときは同じ値を渡す。新しい申請は作られず、前の申請が返る / Pass the same value when retrying the same payment; the earlier request is returned instead of creating a new one
merchantstringyes支払先のサービス名や店名 / merchant or service name (e.g. OpenAI API, AWS)
reasonstringyesなぜこの支払いが必要か。持ち主が承認するときに読む / why this payment is needed (the owner reads this)
recurringstring–サブスク・定期購入・自動更新なら、その間隔を必ず指定する。定期購入は金額に関係なく持ち主の承認が必要 / If this starts or renews a subscription or any recurring charge, set the billing interval. Recurring charges always need the owner's approval, wha…
wait_for_approval_secondsinteger–承認待ちのとき待つ秒数(最大45秒) / seconds to wait for approval

No output schema declared.

No examples provided.

Install

How do I install the Saifuban MCP server?

Saifuban is a hosted endpoint at https://zrphnuvrsldcycxtdftv.supabase.co/functions/v1/saifuban-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 · zrphnuvrsldcycxtdftv.supabase.co

# add to Claude Code
claude mcp add --transport http ut181749ut-saifuban 'https://zrphnuvrsldcycxtdftv.supabase.co/functions/v1/saifuban-mcp'
Common questions

What is the Saifuban MCP server?

Saifuban is an MCP server listed in the public MCP registry as io.github.ut181749ut/saifuban. Hard daily caps on AI agents' API spend, plus phone approval before any other payment. This page covers its hosted endpoint (https://zrphnuvrsldcycxtdftv.supabase.co/functions/v1/saifuban-mcp).

Is the Saifuban MCP server safe to use?

Saifuban scores 82 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 Saifuban MCP server expose?

Saifuban exposes 4 tools: request_payment, check_payment_status, list_payments, get_budget. Their descriptions and schemas cost roughly 840 tokens of context every time the server is loaded.

Does the Saifuban MCP server require authentication?

Yes. Saifuban asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Saifuban MCP server still maintained?

Saifuban 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 Saifuban MCP server?

VerifyMCP ran 13 checks on Saifuban, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. 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.