Skip to content

Japan Agent API MCP server

io.github.mk-career-planning/japan-agent-apimk-career-planningstreamable-httpv0.4.1Scanned

Japan JMA warnings, typhoons, volcano levels and municipality code history in English; x402 checks

8 tools: 6 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 6 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 5
  • Can send data out · 0
  • 1 finding

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 Japan Agent API MCP server can do

The Japan Agent API MCP server is published by the GitHub account mk-career-planning. It has 8 tools. It can create or change data (6 tools: jp_warnings, jp_typhoons, jp_volcanoes, jp_municipality and 2 more), but cannot delete data. 2 tools only read.

5 tools bring in text other people can write (jp_warnings, jp_typhoons, jp_volcanoes and 2 more).

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 21, 2026, version 0.4.1.

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.

8 tools

Changes things 6Claude Code: ask
  • jp_municipalityWhich code does this Japanese municipality have on a date (default today)?1 finding

    Why it is in this group

    • The input takes a statement or command to run (input.code), which can change anything it can reach.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "jp_municipality" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true}; The input takes a statement or command to run (input.code), which can change anything it can reach.

      What this check looks for
    Description, as the server wrote it
    Which code does this Japanese municipality have on a date (default today)? Give a 5/6-digit code, or prefecture and name (old names OK). Returns status mapped / split_candidates / unknown / invalid, the valid code with English and Japanese names, change type and date (merger, incorporation, division, designated city, name change), confirmed JMA warning areas only, and J-LIS convenience-store certificate availability for 8 certificate types. Facts only, from e-Stat LOD (CC BY 4.0) and J-LIS.

    Annotations the server declares

    • readOnlyHint: true
  • jp_municipality_batchWhich codes are valid on a date for up to 50 Japanese municipalities?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
    Which codes are valid on a date for up to 50 Japanese municipalities? e-Stat LOD change history (CC BY 4.0): status mapped / split_candidates (all successors, not apportioned) / unknown / invalid, the code valid on as_of with English and Japanese names, change type and date, confirmed JMA warning areas only, and J-LIS convenience-store certificate availability (available / not_listed / unknown). Facts only; no document preparation or legal advice. Retrying with the same payment is not charged.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • jp_trip_impact_checkDoes a JMA warning or advisory in effect now match a stop on this Japan itinerary [{date, prefecture}]?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
    Does a JMA warning or advisory in effect now match a stop on this Japan itinerary [{date, prefecture}]? Per stop: matched_advisory (with severity), no_match_in_checked_sources (NOT a statement of no impact) or unknown (no data, or date not today/tomorrow JST). Returns checked/unchecked areas and sources, issued_at, retrieved_at, and current JMA typhoon/volcano bulletins (listed, not matched). No forecast. No charge if all stops are unknown. Retries with the same payment are free (get_receipt).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • jp_typhoonsWhich typhoons is JMA issuing bulletins for right now, and what do the bulletins forecast?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
    Which typhoons is JMA issuing bulletins for right now, and what do the bulletins forecast? Number, name, center position, central pressure, maximum wind, issue time, and forecast-circle centers, radii and times, relayed as structured JSON from JMA bulletins (VPTW60-65). No independent forecast, interpolation or track extension.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • jp_volcanoesWhat is the current JMA Volcanic Alert Level (1-5, or warning kind) of this volcano or of every JMA-monitored volcano?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
    What is the current JMA Volcanic Alert Level (1-5, or warning kind) of this volcano or of every JMA-monitored volcano? Name in English or Japanese, or 3-digit JMA code. Returns JMA English and Japanese names, level, previous level and change, issue time, prefectures named in JMA bulletins, source URL and freshness receipt. Relay only; no forecast or interpretation. Gaps filled from JMA website lists (newer wins). No JMA source seen = not_seen_in_checked_feeds, never assumed level 1.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • jp_warningsWhich JMA weather emergency warnings, warnings and advisories are in effect in this Japanese prefecture now?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
    Which JMA weather emergency warnings, warnings and advisories are in effect in this Japanese prefecture now? Structured JSON in English and Japanese (type, level, status, areas with JMA's English names, issued_at, source URL). Relay only; no independent forecast.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
Only reads 2Show 2 read-only tools
  • catalogList the tools of this server with prices, data sources, licensing, daily limits and data freshness.No findings

    Why it is in this group

    • The description's first verb is "list": a word for reading.
    Description, as the server wrote it
    List the tools of this server with prices, data sources, licensing, daily limits and data freshness.

    Annotations the server declares

    • readOnlyHint: true
  • get_receiptRe-fetch the stored result of a settled paid call (e.g.No findings

    Why it is in this group

    • The name "get_receipt" says "get": a word for reading.
    Description, as the server wrote it
    Re-fetch the stored result of a settled paid call (e.g. jp_trip_impact_check) by its receipt_id, for when the response was lost after payment. Free. Unknown or unsettled receipt ids return RECEIPT_NOT_FOUND. Results are kept for 30 days after settlement.

    Annotations the server declares

    • readOnlyHint: true

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 write5
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:08 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
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://japan-agent-api-production.mk-career-planning.workers.dev/mcp: tools/list returned 8 tools to an anonymous client, including jp_warnings (write), jp_typhoons (write), jp_volcanoes (write), jp_municipality (write), jp_trip_impact_check (write) and 1 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "jp_municipality" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true}; The input takes a statement or command to run (input.code), which can change anything it can reach.

    What this check looks for

History

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

  1. Tools2 changed.~2 changedView diff

Install

Pinned to version 0.4.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http japan-agent-api https://japan-agent-api-production.mk-career-planning.workers.dev/mcp
claude mcp add --transport http japan-agent-api https://japan-agent-api-production.mk-career-planning.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__japan-agent-api__catalog",
      "mcp__japan-agent-api__get_receipt"
    ],
    "ask": [
      "mcp__japan-agent-api__jp_warnings",
      "mcp__japan-agent-api__jp_typhoons",
      "mcp__japan-agent-api__jp_volcanoes",
      "mcp__japan-agent-api__jp_municipality",
      "mcp__japan-agent-api__jp_trip_impact_check",
      "mcp__japan-agent-api__jp_municipality_batch"
    ],
    "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 japan-agent-api. Review it before you use it.

Capability tags behind 5 rules
  • mcp__japan-agent-api__jp_warnings untrusted-input
  • mcp__japan-agent-api__jp_typhoons untrusted-input
  • mcp__japan-agent-api__jp_volcanoes untrusted-input
  • mcp__japan-agent-api__jp_trip_impact_check untrusted-input
  • mcp__japan-agent-api__jp_municipality_batch untrusted-input

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.mk-career-planning/japan-agent-api/verify?hash=d00099d9d789e5b11488e2cdea4b753669170d6f06e17ac352f8d0a4de4c38b9" | jq -e '.changed == false'

Pinned hash d00099d9d789, from Nov 21, 2026, 01:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.mk-career-planning/japan-agent-api/changes.xml

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

Badge

Anlyon Radar badge for io.github.mk-career-planning/japan-agent-api
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.mk-career-planning/japan-agent-api.svg)](https://radar.anlyon.com/servers/io.github.mk-career-planning/japan-agent-api)

Source: MCP Registry. Synced Oct 21, 2026, 18:41 UTC.

Japan Agent API MCP server: questions and answers

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

Is the Japan Agent API MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 6 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Japan Agent API MCP server delete data?

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

Can the Japan Agent API 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 Japan Agent API MCP server have?

8 tools: 6 write, 2 read. jp_warnings, jp_typhoons, jp_volcanoes, jp_municipality, jp_trip_impact_check, jp_municipality_batch, catalog and get_receipt.

Does the Japan Agent API MCP server need sign-in or OAuth?

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

Does the Japan Agent API MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Japan Agent API MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 6, 2026. Every change is on this page and in its Atom feed.