Skip to main content
Glama
nishota

Poi MCP Server

by nishota
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Poi MCP Server

English | 日本語

A server that exposes Poi's public API as MCP (Model Context Protocol) tools. From compatible LLM clients (Claude Code / Claude Desktop, etc.), you can call file upload/download, comment read/post, and free license key issuance as "tools".

About Poi

Poi is a simple hosting service for temporarily publishing static web content — no server setup required. Upload a ZIP (a multi-file site), a single HTML file, or a Markdown document, and you instantly get a public URL of the form https://s.poi-plane.com/s/<slug>/.

  • Instant publishing — a drag-and-drop or API upload returns a shareable URL right away.

  • Supported content — .zip (a whole site), .html/.htm (a single page), and .md/.markdown (rendered to a styled page; the original .md stays downloadable).

  • Auto-expiry — every published page is automatically deleted after 7 days.

  • Visitor comments — each public site has a comment area that visitors can read and post to.

  • Not indexed — pages carry noindex, so search engines don't list them (but anyone who knows the URL can view them).

  • License keys — uploading requires a license key (LIC-…). A paid key costs 300 JPY per year; free keys can also be issued (see poi_issue_free_license).

  • Limits — up to 200 MB and 2,000 files per upload; no server-side execution (PHP/CGI) and no password protection.

This MCP server lets an LLM client drive all of the above through tools.

Under the hood it calls Poi's public API:

  • poi_upload → POST /api/v1/upload.php

  • poi_download → GET /api/v1/download.php

  • poi_check_license → GET /api/v1/license.php

  • poi_list_comments → GET /api/v1/comments.php

  • poi_post_comment → POST /api/v1/comments.php

  • poi_issue_free_license → POST /api/v1/issue-free.php

Related MCP server: harness_to_mcp

Tools

Tool

Arguments

Description

poi_upload

path (local file) / content + filename (inline text) / apiKey (optional)

Upload a file and return its public URL. Supported formats: .zip / .html·.htm / .md·.markdown.

poi_download

slug (required; the part of the public URL /s/<slug>/) / dir (destination; defaults to current directory) / filename (optional)

Download and save the contents of a public site. Markdown sites are saved as the original .md; everything else as a whole-site .zip. No authentication required.

poi_check_license

key (optional; falls back to env var POI_API_KEY)

Check whether a license key (LIC-…) is valid, returning OK/NG (valid) and expiry (expires_at / days_left). No authentication required.

poi_list_comments

slug (required)

Fetch a public site's visitor comments, newest first. No authentication required.

poi_post_comment

slug (required) / body (required; max 2000 chars) / author (optional = anonymous)

Post a comment to a public site. No authentication required (repeated posts are rate-limited per IP = 429 rate_limited).

poi_issue_free_license

password (optional; falls back to env var)

Issue a free license key (LIC-…, valid for 1 month / 30 days). The returned key can be used as poi_upload's apiKey.

Setup

It is published on npm, so cloning or npm install is not required. Just specify npx -y poi-mcp as your client's launch command and it will be downloaded and started automatically on first run.

  • Requirements: Node.js 18 or later (npx is enough; uses fetch / FormData / Blob)

  • To pin a version, specify it like npx -y poi-mcp@1.

Only if you want to develop or modify it locally, clone the repository, run cd mcp && npm install, and replace the launch command with node src/index.mjs.

Try it for free

You can try everything without buying a license. The issue password below is deliberately public for trial use — use it to issue your own free license key:

QyOvsWFAw4upl2a1ULJXc9EMKNZh5ozq

  1. Set it as POI_ISSUE_PASSWORD (see the client examples below), or pass it per call via the password argument.

  2. Ask your LLM client to run poi_issue_free_license() — it returns a LIC-… key.

  3. Use that key as POI_API_KEY (or poi_upload's apiKey) to upload.

  • Free keys are valid for 30 days; issuance is rate-limited per IP.

  • Published sites still expire after 7 days as usual.

  • You can also get a free key in the browser at poi-plane.com.

Environment variables

Variable

Default

Purpose

POI_BASE_URL

https://poi-plane.com

Poi base URL

POI_API_KEY

(none)

Required when using the API (uploads). The API key for uploads (master key or license key LIC-…). Using the API requires a license fee of 300 JPY per year.

POI_ISSUE_PASSWORD

(none)

Required when obtaining (issuing) a license key. The issue password for the license key.

POI_API_KEY / POI_ISSUE_PASSWORD can also be overridden per call via tool arguments (apiKey / password).

Registering with a client

Claude Code (CLI)

claude mcp add poi \
  --env POI_BASE_URL=https://poi-plane.com \
  --env POI_API_KEY=LIC-XXXX-XXXX-XXXX-XXXX \
  --env POI_ISSUE_PASSWORD=your-issue-password \
  -- npx -y poi-mcp

Claude Desktop / config file (.mcp.json or claude_desktop_config.json)

{
  "mcpServers": {
    "poi": {
      "command": "npx",
      "args": ["-y", "poi-mcp"],
      "env": {
        "POI_BASE_URL": "https://poi-plane.com",
        "POI_API_KEY": "LIC-XXXX-XXXX-XXXX-XXXX",
        "POI_ISSUE_PASSWORD": "your-issue-password"
      }
    }
  }
}

Manual verification

You can check interactively with the MCP Inspector:

npx @modelcontextprotocol/inspector node src/index.mjs

Usage examples (instructions to the LLM)

  • "Upload site.zip bundling ./dist to Poi and tell me the URL" → poi_upload({ path: "./site.zip" })

  • "Publish this HTML as page.html" → poi_upload({ content: "<h1>hi</h1>", filename: "page.html" })

  • "Download 9KwR7jgeDfPr to my machine" → poi_download({ slug: "9KwR7jgeDfPr" }) (Markdown sites save .md, others save .zip)

  • "Check whether this license key is still valid" → poi_check_license({ key: "LIC-XXXX-XXXX-XXXX-XXXX" }) → { valid, expires_at, days_left, ... }

  • "List the comments on 9KwR7jgeDfPr" → poi_list_comments({ slug: "9KwR7jgeDfPr" })

  • "Post 'Nice!' as a comment on 9KwR7jgeDfPr" → poi_post_comment({ slug: "9KwR7jgeDfPr", body: "Nice!" }) (omit author for anonymous)

  • "Get a free key for uploading" → poi_issue_free_license() (uses the issue password from env vars)

API keys and issue passwords are secrets (the trial issue password above is an exception — it is public by design). In shared environments, pass them via environment variables and be careful not to leave them in logs or conversations.

Publishing (for maintainers)

To make npx -y poi-mcp work, publish this mcp/ to npm.

cd mcp
npm login
npm version patch        # bump the version as needed
npm publish --access public

  • If the package name poi-mcp is already taken, change name in package.json to a scoped name (e.g. @you/poi-mcp), and read poi-mcp in the README and docs accordingly.

  • Only files (src and README.md) are published. node_modules is not included.

Poi MCP サーバー（日本語）

English | 日本語

Poiの外部公開 API を MCP（Model Context Protocol）ツールとして公開するサーバーです。 対応する LLM クライアント（Claude Code / Claude Desktop など）から、ファイルのアップロード・ ダウンロード、コメントの取得・投稿、無料ライセンスキーの発行を「ツール」として呼び出せます。

Poi とは

Poi は、静的な Web コンテンツを手軽に一時公開できるホスティングサービスです。 サーバーの用意は不要。ZIP（複数ファイルのサイト）・単体 HTML・Markdown をアップロードすると、 https://s.poi-plane.com/s/<slug>/ 形式の公開 URL がその場で発行されます。

  • すぐ公開 — ドラッグ&ドロップ、または API でアップロードすると共有 URL がすぐ返ります。

  • 対応コンテンツ — .zip（サイト一式）・.html/.htm（単体ページ）・.md/.markdown （整形済みページとして表示。原本 .md もダウンロード可能）。

  • 自動失効 — 公開ページは 7 日で自動的に削除されます。

  • 訪問者コメント — 各公開サイトに、訪問者が読み書きできるコメント欄があります。

  • 検索非対象 — ページには noindex が付き、検索エンジンには載りません（URL を知っていれば誰でも閲覧可）。

  • ライセンスキー — アップロードにはライセンスキー（LIC-…）が必要です。有料キーは 1 年間 300 円、無料キーの発行も可能です（poi_issue_free_license を参照）。

  • 上限 — 1 回のアップロードで最大 200 MB・2,000 ファイル。サーバー実行（PHP/CGI）やパスワード保護は非対応。

この MCP サーバーは、上記のすべてを LLM クライアントからツールとして操作できるようにします。

内部では Poi の公開 API を叩きます:

  • poi_upload → POST /api/v1/upload.php

  • poi_download → GET /api/v1/download.php

  • poi_check_license → GET /api/v1/license.php

  • poi_list_comments → GET /api/v1/comments.php

  • poi_post_comment → POST /api/v1/comments.php

  • poi_issue_free_license → POST /api/v1/issue-free.php

ツール

ツール

引数

説明

poi_upload

path（ローカルファイル）／ content + filename（テキスト直指定）／ apiKey（任意）

ファイルをアップロードして公開 URL を返す。対応形式 .zip / .html・.htm / .md・.markdown。

poi_download

slug（必須。公開 URL /s/<slug>/ の部分）／ dir（保存先。既定はカレント）／ filename（任意）

公開サイトの中身をダウンロードして保存する。Markdown サイトは原本 .md、それ以外はサイト全体 .zip。認証不要。

poi_check_license

key（任意。未指定なら環境変数 POI_API_KEY）

ライセンスキー（LIC-…）が有効かを判定し、OK/NG（valid）と有効期限（expires_at / days_left）を返す。認証不要。

poi_list_comments

slug（必須）

公開サイトの訪問者コメントを新しい順に取得する。認証不要。

poi_post_comment

slug（必須）／ body（必須。最大 2000 字）／ author（任意＝匿名）

公開サイトにコメントを投稿する。認証不要（連投は IP 単位でレート制限＝ 429 rate_limited）。

poi_issue_free_license

password（任意。未指定なら環境変数）

無料ライセンスキー（LIC-…, 1 か月＝30 日有効）を発行。返ったキーは poi_upload の apiKey に使える。

セットアップ

npm に公開してあるので、クローンや npm install は不要です。クライアントの起動コマンドに npx -y poi-mcp を指定すれば、初回に自動でダウンロードされて起動します。

  • 必要なもの: Node.js 18 以上（npx が使えれば OK。fetch / FormData / Blob を使用）

  • バージョンを固定したいときは npx -y poi-mcp@1 のように指定します。

ローカルで開発・改造する場合のみ、リポジトリを clone して cd mcp && npm install、 起動コマンドを node src/index.mjs に置き換えてください。

お試し（無料キーの発行）

ライセンスを購入しなくても一通り試せます。以下の発行パスワードはお試し用に公開している ものです。これを使って自分用の無料ライセンスキーを発行してください:

QyOvsWFAw4upl2a1ULJXc9EMKNZh5ozq

  1. POI_ISSUE_PASSWORD に設定する（下記のクライアント登録例を参照）か、password 引数で都度渡す

  2. LLM クライアントに poi_issue_free_license() を実行させる → LIC-… のキーが返る

  3. 返ったキーを POI_API_KEY（または poi_upload の apiKey）に設定してアップロード

  • 無料キーの有効期間は 30 日。発行は IP 単位でレート制限されます

  • 公開サイトは通常どおり 7 日で失効します

  • ブラウザから poi-plane.com で取得することもできます

環境変数

変数

既定

用途

POI_BASE_URL

https://poi-plane.com

Poi のベース URL

POI_API_KEY

（なし）

API 利用時に必要なアップロード用 API キー（マスターキー or ライセンスキー LIC-…）。API の利用には 1 年間 300 円のライセンス料が必要です。

POI_ISSUE_PASSWORD

（なし）

ライセンスキーを取得（発行）するときに必要な発行パスワード

POI_API_KEY / POI_ISSUE_PASSWORD はツール引数（apiKey / password）で都度上書きもできます。

クライアントへの登録

Claude Code（CLI）

claude mcp add poi \
  --env POI_BASE_URL=https://poi-plane.com \
  --env POI_API_KEY=LIC-XXXX-XXXX-XXXX-XXXX \
  --env POI_ISSUE_PASSWORD=発行パスワード \
  -- npx -y poi-mcp

Claude Desktop / 設定ファイル（.mcp.json や claude_desktop_config.json）

{
  "mcpServers": {
    "poi": {
      "command": "npx",
      "args": ["-y", "poi-mcp"],
      "env": {
        "POI_BASE_URL": "https://poi-plane.com",
        "POI_API_KEY": "LIC-XXXX-XXXX-XXXX-XXXX",
        "POI_ISSUE_PASSWORD": "発行パスワード"
      }
    }
  }
}

動作確認（手動）

MCP Inspector で対話的に確認できます:

npx @modelcontextprotocol/inspector node src/index.mjs

使い方の例（LLM への指示）

  • 「./dist をまとめた site.zip を Poi にアップロードして URL を教えて」 → poi_upload({ path: "./site.zip" })

  • 「この HTML を page.html として公開して」 → poi_upload({ content: "<h1>hi</h1>", filename: "page.html" })

  • 「9KwR7jgeDfPr を手元にダウンロードして」 → poi_download({ slug: "9KwR7jgeDfPr" })（Markdown サイトは .md、それ以外は .zip を保存）

  • 「このライセンスキーがまだ有効か確認して」 → poi_check_license({ key: "LIC-XXXX-XXXX-XXXX-XXXX" }) → { valid, expires_at, days_left, ... }

  • 「9KwR7jgeDfPr のコメントを一覧して」 → poi_list_comments({ slug: "9KwR7jgeDfPr" })

  • 「9KwR7jgeDfPr に『いいね！』とコメントして」 → poi_post_comment({ slug: "9KwR7jgeDfPr", body: "いいね！" })（author 省略で匿名）

  • 「アップロード用の無料キーを取って」 → poi_issue_free_license()（環境変数の発行パスワードを使用）

API キー・発行パスワードは秘密情報です（上記のお試し用発行パスワードは公開前提の例外です）。共有環境では環境変数で渡し、ログや会話に残さないよう注意してください。

公開（メンテナ向け）

npx -y poi-mcp を成立させるには、この mcp/ を npm に公開します。

cd mcp
npm login
npm version patch        # 必要に応じて版を上げる
npm publish --access public

  • パッケージ名 poi-mcp が取得済みの場合は、package.json の name をスコープ付き （例 @あなた/poi-mcp）に変え、README とドキュメントの poi-mcp も読み替えてください。

  • 公開されるのは files（src と README.md）のみです。node_modules は含まれません。

Available Tools

6 tools
poi_check_licensePoi: ライセンスキーの有効性を確認A

ライセンスキー（LIC-…）が有効かを判定し、OK/NG（valid）と有効期限（expires_at・残り日数 days_left）を返します。key を省略すると環境変数 POI_API_KEY を確認します。認証は不要。

ParametersJSON Schema
NameRequiredDescriptionDefault
keyNo確認するライセンスキー（未指定なら環境変数 POI_API_KEY を使用）

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses key behavioral traits: it is a read-only operation (no side effects), returns specific fields (valid, expires_at, days_left), and requires no authentication. With no annotations provided, this level of detail is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, efficiently conveying purpose, input handling, and output details. No redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (1 optional parameter, no output schema), the description fully explains input, behavior, and return values (valid, expires_at, days_left). It addresses the env var fallback and auth requirements, leaving no major gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema parameter 'key' has 100% coverage (description in schema matches description). However, the tool description adds extra context: the key format (LIC-…) and the fallback to environment variable, which aids understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: determining if a license key (with format LIC-…) is valid, and returning validity status and expiration details. It is distinct from sibling tools (poi_download, poi_issue_free_license, etc.), which do not perform license checking.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit context: it mentions that omitting the key checks the environment variable POI_API_KEY and that authentication is not required. While it does not explicitly list alternatives, the sibling tools indicate this is the only license-check tool, so usage guidance is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

poi_downloadPoi: 公開サイトをダウンロードA

slug を指定して公開サイトの中身をダウンロードし、ローカルに保存します。Markdown サイトは原本の .md、それ以外（ZIP・単体 HTML から作ったサイト）はサイト全体の .zip を保存します。認証は不要（slug を知っていれば取得可）。保存先パス・種別・サイズを返します。

ParametersJSON Schema
NameRequiredDescriptionDefault
dirNo保存先ディレクトリ（未指定ならカレントディレクトリ）
slugYes公開サイトの slug（公開 URL /s/<slug>/ の <slug> 部分）
filenameNo保存ファイル名（未指定ならサーバー指定の名前）

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses that authentication is not required, the return includes path/type/size, and the handling differs by site type (md vs zip). However, it omits potential errors (e.g., invalid slug) or size limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loading the main action and essential details. Every sentence provides meaningful information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and 3 parameters, the description covers core download behavior, return values, and constraints. It could be more complete on error handling (e.g., invalid slug) or idempotency, but it is sufficient for basic use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds value by explaining the slug format (from /s/<slug>/) and the file type logic (md vs zip) beyond the schema's parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool downloads a public POI site by slug and saves it locally, specifying that Markdown sites save as .md and others as .zip. This distinguishes it from sibling tools like poi_upload (upload) and poi_list_comments (list comments).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for downloading public sites but does not explicitly state when to use this tool versus alternatives (e.g., when to use poi_upload instead). No when-not-to-use guidance is provided, though the context of siblings hints at the tool's niche.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

poi_issue_free_licensePoi: 無料ライセンスキーを発行A

発行パスワードを使って無料ライセンスキー（LIC-…, 1 か月有効）を発行します。発行されたキーは poi_upload の apiKey（または環境変数 POI_API_KEY）に使えます。

ParametersJSON Schema
NameRequiredDescriptionDefault
passwordNo発行パスワード（未指定なら環境変数 POI_ISSUE_PASSWORD を使用）

TDQS

A3.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It discloses the license validity (1 month) and usage for poi_upload, but does not mention any side effects, destructive behavior, idempotency, or authorization details beyond the password.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core action, and contains no redundant information. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one optional parameter, the description is adequate. It explains what the license key is and how it is used. It lacks details on failure modes or outcomes, but is sufficient for basic usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and already describes the password parameter well. The description adds marginal value by repeating the parameter's purpose, but does not provide additional details beyond what the schema offers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it issues a free license key (LIC-..., valid 1 month) using an issue password, and that the key can be used for poi_upload. It distinguishes itself from siblings by specifying the exact purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use (when needing a free license key) and how to provide the password (via parameter or environment variable). It doesn't explicitly state when not to use or contrast with sibling tools, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

poi_list_commentsPoi: サイトのコメント一覧を取得A

slug を指定して、公開サイトに付いた訪問者コメントを新しい順に取得します。認証は不要。

ParametersJSON Schema
NameRequiredDescriptionDefault
slugYes公開サイトの slug（公開 URL /s/<slug>/ の <slug> 部分）

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description is expected to disclose behavioral traits. It states the operation is a retrieval (implies read-only) and that comments are ordered by newest. It does not mention rate limits, pagination, or potential errors, but the information is adequate for basic understanding.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that conveys all essential information: the required parameter, the action, the ordering, and authentication requirement. No redundant words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (one parameter, no output schema), the description covers the core functionality. However, it omits details about return format, pagination, or error handling, which could be important for an agent to use the tool correctly in all scenarios.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage with a clear description for 'slug'. The tool description adds value beyond the schema by noting the ordering (newest first) and that no authentication is needed, enhancing the agent's understanding of parameter context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the verb '取得' (retrieve) and specifies the resource '訪問者コメント' (visitor comments) for a public site, clearly indicating the tool's function. While it distinguishes from siblings like 'poi_post_comment', it does not explicitly differentiate from other read tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions that authentication is not required, which is a helpful usage note. However, it does not provide explicit guidance on when to use this tool versus alternatives, nor does it specify when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

poi_post_commentPoi: サイトにコメントを投稿A

slug を指定して、公開サイトにコメントを投稿します。author は省略可（省略時は匿名）。body は最大 2000 文字。認証は不要。

ParametersJSON Schema
NameRequiredDescriptionDefault
bodyYesコメント本文（1〜2000 文字）
slugYes公開サイトの slug（公開 URL /s/<slug>/ の <slug> 部分）
authorNo表示名（省略で匿名）

TDQS

A4.1/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden. It discloses that authentication is not required and that body has a character limit. However, it does not describe the result of the operation (e.g., success indication, returned data) or potential side effects (e.g., whether a duplicate comment is allowed).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: three sentences that front-load the purpose and then provide key constraints. Every sentence adds necessary information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers authentication, optional parameters, and limits, but lacks information about the return value (no output schema) and error conditions. For a creation tool, this is a notable gap in completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All parameters are described in the schema (100% coverage). The description adds value by clarifying that 'author' defaults to anonymous when omitted and specifying the exact character limit for 'body', which is not in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the action ('post a comment') and the target ('public site' identified by slug). It is specific and clearly distinguishes from sibling tools like poi_list_comments (listing) and poi_upload (file upload).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear constraints: author optional (anonymous if omitted), body max 2000 chars, no authentication required. However, it does not explicitly state when not to use this tool or mention alternatives beyond the sibling context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

poi_uploadPoi: ファイルをアップロードして公開 URL を発行A

ローカルファイル(path) か、テキスト内容(content + filename) をアップロードし、公開 URL を発行します。対応形式は .zip / .html・.htm / .md・.markdown。公開ページは 7 日で自動失効します。

ParametersJSON Schema
NameRequiredDescriptionDefault
pathNoアップロードするローカルファイルの絶対/相対パス
apiKeyNoAPI キー（未指定なら環境変数 POI_API_KEY を使用）
contentNoテキストを直接アップロードする場合の本文（filename 必須）
filenameNocontent を使う場合のファイル名（例: page.html, note.md）

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses that the tool uploads files, issues public URLs, supports specific formats, and auto-expires in 7 days. Key traits like authentication (via apiKey) and non-destructive nature are implied but not explicitly stated. Overall, it provides sufficient behavioral context beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, consisting of three short sentences that each add distinct value: purpose, supported formats, and expiration. No fluff; front-loaded with the primary action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the description covers key aspects (purpose, modes, formats, expiration), it lacks details on return value format (though implied to be a URL) and behavior when both path and content are provided. With no output schema, more information on the response structure would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds value by grouping parameters into two usage modes (path vs. content+filename), which clarifies the interdependence. This grouping enhances understanding beyond individual parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: upload local files or text content to generate a public URL. Supported formats and automatic expiration are explicitly mentioned, making the tool's function specific and distinct from sibling tools like download or license management.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains two usage modes (path or content+filename) and lists supported formats and expiration duration. While it does not explicitly contrast with sibling tools, the functions are sufficiently different that no additional guidance is necessary. However, it could be improved by clarifying when to use each mode.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 6 tool updatesv1.0.1
    • First observedpoi_check_license
    • First observedpoi_download
    • First observedpoi_issue_free_license
    • First observedpoi_list_comments
    • First observedpoi_post_comment
    • First observedpoi_upload
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored across 6 tools

Disambiguation5/5

Each tool targets a distinct action: license checking versus issuance, downloading versus uploading, and commenting operations are separate. There is no overlap in functionality.

Naming Consistency5/5

All tools follow a consistent 'poi_verb_noun' pattern, with clear verbs like check, download, issue, list, post, upload. The naming is predictable and unambiguous.

Tool Count5/5

With 6 tools covering license management, content upload/download, and commenting, the set is well-scoped for the server's purpose. Each tool earns its place.

Completeness4/5

Core workflows (upload, download, license management, comments) are covered, but missing operations like delete or update for sites and comments create minor gaps.

Maintenance

ActivityStale
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers