thePaymentsNotes Ledger

by alwaysarafath · remote · no sign-in to list tools · v0.3.0-testnet · published by GitHub user alwaysarafath

Verified agentic-commerce protocol status + merchant agent-readiness reports. Free on testnet.

Changes · 2

Compare Registry entry

5 tools: 2 change things and 3 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things2Claude Code: ask: see these tools
Only reads3Claude Code: allow: see these tools

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http thepaymentsnotes-ledger https://tpn-gateway.alwaysarafath.workers.dev/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

5 tools

Changes things 2Creates or changes something that can be changed back.Claude Code: ask

check_agent_readinessFree on testnet.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
Free on testnet. Automated scan, not human-verified. Scan-only quick read of whether AI agents can discover and buy from a website. Returns the engine's report as-is: scanner_version and scan_id ("v4"), report.score (scan-only), report.band (can be 'Partly assessed'), report.coverage, report.summary, report.confidence, report.can_agents_buy, report.who_eats_the_loss (display label "Who carries the risk?"; needs the 5 answers, so not assessed here), report.archetype ('unclassified' if not classified), report.rows (with unknown_reason), report.gaps, report.actions (always exactly 3: 2 business then 1 technical, each with kind "business" | "technical"), report.ledger (related Ledger entries), checks, evidence, findings, and scan_interrupted.reason (timeout|blocked|dns_tls|robots_disallowed|refused|http_error) when the scan could not finish. Input: a bare domain (e.g. "yourstore.com"). It reads public pages only; it is NOT a certification, audit or legal advice. Open questions only the business can answer come back with a link to https://thepaymentsnotes.com/readiness. Limits: 3 scans per caller per day and 50 per day overall, shared with the website; results are cached for 24h. Weekly newsletter: https://thepaymentstack.substack.com
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
whats_newFree on testnet.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Free on testnet. Recent verified Ledger changes since a date (last 30 days, max 5 items): headline, status, date, one source.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

Only reads 3Looks things up and changes nothing.Claude Code: allow

get_statusFree on testnet.No findings
Why it is in this group
- The name "get_status" says "get": a word for reading.
Description, as the server wrote it
Free on testnet. Status of one Ledger row (protocol, platform, wallet or stablecoin) from the human-verified Ledger: headline, status, last verified date and ONE source URL. If the name is not in the Ledger: result="unknown" plus up to 3 did_you_mean names (never a guessed answer). Call list_protocols to see every name.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_status_detailFree on testnet (no payment, no wallet needed).No findings
Why it is in this group
- The name "get_status_detail" says "get": a word for reading.
Description, as the server wrote it
Free on testnet (no payment, no wallet needed). Fuller answer for ONE Ledger row (protocol, platform, wallet or stablecoin): headline, status (authoritative), maturity (a plain-English stage derived from status, never contradicts it), steward, what_this_means (the detail after the headline, omitted if there is none), latest update date, verified date and up to 3 sources. Unknown names return result="unknown" with up to 3 did_you_mean names. Call list_protocols to see every name.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_protocolsFree on testnet.No findings
Why it is in this group
- The name "list_protocols" says "list": a word for reading.
Description, as the server wrote it
Free on testnet. Every row in the human-verified Ledger (protocols, platforms, wallets, stablecoins): name, short names/aliases and status only. Use a name from here with get_status or get_status_detail.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

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 outbound.

Reads private data0: Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; check_agent_readiness
Can send data out0: 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.

Looked at Oct 22, 2026, 14:56 UTC, unchanged since Oct 22, 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: 2
Protocol version: 2025-06-18
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: none
RFC 9728 protected resource metadata: none
Authorization servers: none
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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
Matched text
https://tpn-gateway.alwaysarafath.workers.dev/mcp: tools/list returned 5 tools to an anonymous client, including check_agent_readiness (write), whats_new (write)
What this check looks for

Install

Pinned to version 0.3.0-testnet. Values in angle brackets are yours to fill in.

claude mcp add --transport http thepaymentsnotes-ledger https://tpn-gateway.alwaysarafath.workers.dev/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": [
      "mcp__thepaymentsnotes-ledger__list_protocols",
      "mcp__thepaymentsnotes-ledger__get_status",
      "mcp__thepaymentsnotes-ledger__get_status_detail"
    ],
    "ask": [
      "mcp__thepaymentsnotes-ledger__check_agent_readiness",
      "mcp__thepaymentsnotes-ledger__whats_new"
    ],
    "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 thepaymentsnotes-ledger. Review it before you use it.

Capability tags behind 1 rule

mcp__thepaymentsnotes-ledger__check_agent_readiness untrusted-input

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.alwaysarafath/thepaymentsnotes-ledger/changes.xml

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

Anlyon alternative

2 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry. Synced Oct 21, 2026, 18:22 UTC.

For agents: Markdown · JSON · report this listing