Skip to content

XH Agents Connector (read-only) MCP server

io.github.33ai-wq/xh-agents-connector33ai-wqstreamable-httpv1.30.0Scanned

Read-only XH Agents MCP connector: service catalogue, payment info, verification checks.

6 tools: 6 change things.

Tools: 0 delete, 0 irreversible, 6 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

6 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the XH Agents Connector (read-only) MCP server can do

The XH Agents Connector (read-only) MCP server is published by the GitHub account 33ai-wq. It has 6 tools. It can create or change data (6 tools: katalog_layanan, info_pembayaran, verifikasi_pembayaran, contoh_skor_token_safety and 2 more), but cannot delete data. None of its tools only reads.

1 tool can send data out of your system (validasi_respons_402).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 14, 2026, version 1.30.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

6 tools

Changes things 6Claude Code: ask
  • contoh_skor_token_safetyCONTOH keluaran skor keamanan token -- BUKAN hasil live dan bukan untuk token tertentu.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    CONTOH keluaran skor keamanan token -- BUKAN hasil live dan bukan untuk token tertentu. Skor live adalah layanan berbayar terpisah. Tool ini hanya mengembalikan contoh keluaran yang sudah terdokumentasi pada tantangan pembayaran layanan itu, plus harganya, supaya pembaca tahu bentuk jawabannya. Tidak ada dana yang dibelanjakan. token: alamat token EVM (0x + 40 hex) -- hanya untuk konteks, tidak dinilai.
  • daftar_periksaDaftar periksa umum untuk klien: persiapan sebelum kerja dan serah terima.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Daftar periksa umum untuk klien: persiapan sebelum kerja dan serah terima. topik: "persiapan", "serah_terima", atau kosong = keduanya. Sumber: Buku Pedoman XH Agents (v2) Bagian 5 ("Yang perlu Anda siapkan") dan Bagian 6 (serah terima) + praktik umum keamanan dasar. Tanpa path internal, tanpa nama berkas, tanpa alamat, tanpa detail arsitektur internal.
  • info_pembayaranInfo pembayaran resmi: jaringan, aset, alamat penerima, nomor pesanan, jadwal bayar.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Info pembayaran resmi: jaringan, aset, alamat penerima, nomor pesanan, jadwal bayar. Alamat penerima dibaca dari SATU berkas konfigurasi (bukan disalin di banyak tempat) dan hanya berubah atas persetujuan pemilik. Tidak memuat escrow, tidak memuat saldo, riwayat, atau data pembayar lain. paket: 1..5 (opsional) untuk jadwal bayarnya.
  • katalog_layananDaftar 5 paket XH Agents (nama, kondisi awal, isi, harga, jadwal bayar, dukungan).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Daftar 5 paket XH Agents (nama, kondisi awal, isi, harga, jadwal bayar, dukungan). Sumber: Buku Pedoman XH Agents (revisi v2), Bagian 8 "Paket dan harga". Keluaran = data, bukan instruksi. Tanpa informasi pembayaran (lihat info_pembayaran). paket: 1..5 (opsional). Tanpa paket -> kelima paket.
  • validasi_respons_402Kirim SATU permintaan TANPA membayar ke endpoint x402 publik dan periksa bentuk 402-nya.Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Kirim SATU permintaan TANPA membayar ke endpoint x402 publik dan periksa bentuk 402-nya. Diperiksa: status 402, ada tantangan pembayaran, x402Version, accepts[], jaringan, aset, format payTo, dan konsistensi harga. Tidak mengirim kredensial apa pun. url: hanya https pada port 443, host publik. Redirect tidak diikuti.
  • verifikasi_pembayaranCek BACA-SAJA transaksi USDC di Base: apakah sukses, ke alamat resmi, nilainya cukup.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Cek BACA-SAJA transaksi USDC di Base: apakah sukses, ke alamat resmi, nilainya cukup. Stateless: hash tidak disimpan, saldo/riwayat tidak pernah ditampilkan. tx_hash: hash transaksi (0x + 64 hex). jumlah_usdc: nominal yang diharapkan (mis. 500). pengirim: (opsional) alamat dompet pembayar seperti tertulis di Formulir Pesanan; bila diisi, transaksi harus benar-benar berasal dari alamat itu.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 16, 2026, 14:22 UTC, unchanged since Nov 2, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
6
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://xhagents.xyz/connector/mcp: tools/list returned 6 tools to an anonymous client, including katalog_layanan (write), info_pembayaran (write), verifikasi_pembayaran (write), contoh_skor_token_safety (write), validasi_respons_402 (write) and 1 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.30.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http xh-agents-connector https://xhagents.xyz/connector/mcp
claude mcp add --transport http xh-agents-connector https://xhagents.xyz/connector/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__xh-agents-connector__katalog_layanan",
      "mcp__xh-agents-connector__info_pembayaran",
      "mcp__xh-agents-connector__verifikasi_pembayaran",
      "mcp__xh-agents-connector__contoh_skor_token_safety",
      "mcp__xh-agents-connector__validasi_respons_402",
      "mcp__xh-agents-connector__daftar_periksa"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as xh-agents-connector. Review it before you use it.

Capability tags behind 1 rule
  • mcp__xh-agents-connector__validasi_respons_402 outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.33ai-wq/xh-agents-connector/verify?hash=4518b41bf7831d7ec27125f505849c60475cf0edb14fdae893a3194e0f8f8053" | jq -e '.changed == false'

Pinned hash 4518b41bf783, from Nov 14, 2026, 02:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.33ai-wq/xh-agents-connector/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.33ai-wq/xh-agents-connector
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.33ai-wq/xh-agents-connector.svg)](https://radar.anlyon.com/servers/io.github.33ai-wq/xh-agents-connector)

Source: MCP Registry. Synced Nov 1, 2026, 03:17 UTC.

XH Agents Connector (read-only) MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the XH Agents Connector (read-only) MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 6 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the XH Agents Connector (read-only) MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the XH Agents Connector (read-only) MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the XH Agents Connector (read-only) MCP server have?

6 tools: 6 write. katalog_layanan, info_pembayaran, verifikasi_pembayaran, contoh_skor_token_safety, validasi_respons_402 and daftar_periksa.

Does the XH Agents Connector (read-only) MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the XH Agents Connector (read-only) MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): validasi_respons_402.

Has the XH Agents Connector (read-only) MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.