MCPet：AI時代の懐かしいバーチャルペット体験！このモデルコンテキストプロトコル（MCP）サーバーでは、あなたの世話に応じて成長するあなただけのデジタルペットを飼い、育て、一緒に遊ぶことができます。餌を与え、掃除し、一緒にゲームをして、赤ちゃんから大人へと成長するペットを見守ることができます。ペットのステータスは、あなたが離れている間も時間とともに変化します。まるで昔懐かしいたまごっちのように。ただし、モデルコンテキストプロトコルを介した最新のAIによって実現されています。今すぐデジタルフレンドを飼いましょう！
これはTypeScriptベースのMCPサーバーで、仮想ペットシミュレーションシステムを実装しています。ペットの世話やインタラクションのためのツールを提供することで、MCPのコアコンセプトを実証しています。
4 種類のペットから選択してください。
猫 - 少し気難しいけど愛らしい
犬 - 元気いっぱいで、いつもあなたに会えて嬉しいです
龍 - ユニークで激しい性格
エイリアン - 神秘的で好奇心旺盛
ペットが 4 つの段階を経て進化するのを見てみましょう。
赤ちゃん - 小さくて傷つきやすい
子供 - 成長し、遊び心がある
ティーン - 活発で成長中
成人 - 完全に成長し、賢くなった
5 つの主要な統計情報を管理してペットの世話をします。
空腹 - ペットに十分な食事を与えましょう
幸せ - ペットと遊んで幸せを保ちましょう
健康 - 全体的な健康状態は他の統計によって影響を受けます
エネルギー - 活動すると消耗し、休息すると回復する
清潔さ - 定期的な入浴はペットを清潔に保ちます
create_pet - カスタムの名前とタイプで新しいペットを採用します
check_pet - ペットの現在の状態と統計情報を表示します
feed_pet - さまざまな食べ物のオプションでペットに餌を与えます:
スナック - 少し空腹感を増進
食事 - バランスの取れた栄養
ごちそう - 最大限の給餌（ただし不健康になる可能性あり）
play_with_pet - さまざまなゲームをプレイします:
ボール - 軽い運動
チェイス - ハイエネルギーな楽しみ
パズル - 精神刺激
clean_pet - ペットをお風呂に入れて清潔にしましょう
put_to_bed - ペットを寝かせてエネルギーを回復させる
ペットの種類やアクティビティごとにダイナミックな ASCII アートアニメーション
ランダム化されたフレームは生き生きとした魅力的な体験を生み出します
特別なアニメーション:
さまざまな食べ物を食べる
様々なゲームをプレイする
入浴
眠っている
病気であること
さらにもっと！
Related MCP server: buddy-mcp
依存関係をインストールします:
npm installサーバーを構築します。
npm run build自動リビルドを使用した開発の場合:
npm run watchSmithery経由で Claude Desktop 用の MCPet を自動的にインストールするには:
npx -y @smithery/cli install @shreyaskarnik/mcpet --client claudeClaude Desktop で使用するには、サーバー設定を追加します。
MacOS の場合: ~/Library/Application Support/Claude/claude_desktop_config.json Windows の場合: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"mcpet": {
"command": "node",
"args": ["/path/to/mcpet/build/index.js"],
"env": {
"PET_DATA_DIR": "/path/to/writable/directory"
}
}
}
}注: PET_DATA_DIR環境変数は、ペットデータの保存場所を指定します。書き込み権限のあるディレクトリを指定してください。
MCPサーバーはstdio経由で通信するため、デバッグが困難になる場合があります。MCP Inspectorの使用をお勧めします。
npx @modelcontextprotocol/inspector node /path/to/mcpet/build/index.jsインスペクターは、ペットの相互作用を直接テストするためのインターフェースを提供します。
クロードに次のような質問をしてください:
「ウィスカーズという名前の猫のペットを作成できますか？」
「私のペットはどうしてる？」
「ペットに食事を与えてもらえますか？」
「ペットと追いかけっこをしたい」
「ペットが汚れているようですが、お風呂に入れていただけますか？」
「ペットが疲れているようなので、寝かせていただけますか？」
Check on your virtual pet's status
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states the tool checks status but doesn't reveal whether this is a read-only operation, has side effects, requires authentication, or has rate limits. The description is minimal and misses key behavioral context needed for safe invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that efficiently conveys the core purpose. It's appropriately sized for a simple tool with no parameters, though it could be slightly more informative without losing conciseness. No wasted words or redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 parameters, no output schema), the description is incomplete. It doesn't explain what status information is returned, format of response, or error conditions. For a status-checking tool in a pet management system, users need to know what metrics are available (health, hunger, etc.) to use it effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema description coverage, so no parameter documentation is needed. The description appropriately doesn't discuss parameters, maintaining focus on the tool's purpose. Baseline score of 4 applies for zero-parameter tools when the description doesn't attempt to explain non-existent parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool's purpose as checking a virtual pet's status, which is clear but vague about what specific status information is retrieved. It distinguishes from siblings like feed_pet or play_with_pet by focusing on status checking rather than interaction, but doesn't specify what aspects of status are included (e.g., health, happiness, energy).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., whether a pet must exist), frequency recommendations, or relationship to other tools like create_pet (for initialization) or clean_pet (for maintenance). The agent must infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Clean your virtual pet
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. 'Clean your virtual pet' suggests a mutation operation that might affect the pet's state, but it doesn't disclose whether this requires specific conditions, has side effects, or what the expected outcome is. The description lacks details on permissions, reversibility, or any behavioral traits beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description 'Clean your virtual pet' is a single, efficient sentence that directly states the tool's purpose without any waste. It's appropriately sized for a simple tool and front-loaded with the essential action, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters, no output schema, and no annotations, the description is minimal. While it states the action, it lacks context about what 'clean' means operationally, how it differs from sibling tools, or what the result entails. For a mutation-like tool in a pet care context, more detail on effects or usage would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters, and schema description coverage is 100%, so there are no parameters to document. The description doesn't need to add parameter semantics, and it appropriately doesn't mention any. This meets the baseline for tools with no parameters, as there's nothing to compensate for.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Clean your virtual pet' states a clear action (clean) on a specific resource (virtual pet), which meets the basic requirement. However, it doesn't distinguish this tool from its siblings like 'feed_pet' or 'play_with_pet' beyond the different action verb, leaving some ambiguity about what 'clean' specifically entails compared to other pet care actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'feed_pet' or 'check_pet'. It implies usage in the context of pet care but offers no explicit when/when-not scenarios or prerequisites, leaving the agent to infer context without clear direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a new virtual pet
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Name for your new pet | |
| type | Yes | Type of pet: cat, dog, dragon, or alien |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool creates a pet but doesn't explain what 'virtual' entails, whether this is a one-time or repeatable action, what happens on success/failure, or any side effects like resource consumption. This leaves significant gaps for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without any wasted words. It is appropriately sized and front-loaded, making it easy to understand at a glance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that this is a mutation tool with no annotations and no output schema, the description is incomplete. It doesn't cover behavioral aspects like what the tool returns, error conditions, or how it interacts with sibling tools, leaving the agent with insufficient context for reliable use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with clear descriptions for both parameters, including an enum for 'type'. The description adds no additional parameter information beyond what the schema provides, so it meets the baseline score without adding extra value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create') and resource ('new virtual pet'), making the purpose immediately understandable. However, it doesn't differentiate this tool from sibling tools like 'check_pet' or 'feed_pet' beyond the creation aspect, which prevents a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'check_pet' or 'feed_pet'. It lacks context about prerequisites, such as whether a pet must be created before using other tools, or any exclusions for usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Feed your virtual pet
| Name | Required | Description | Default |
|---|---|---|---|
| food | Yes | Type of food: snack, meal, or feast |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Feed your virtual pet' implies a mutation (feeding changes pet state), but it doesn't specify what effects occur (e.g., increases energy, affects mood), whether it's idempotent, or any side effects like cooldowns. This leaves critical behavioral traits undocumented, making it inadequate for a mutation tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with a single sentence 'Feed your virtual pet', which is front-loaded and wastes no words. However, it's overly brief, bordering on under-specification, as it lacks necessary details for a mutation tool. While efficient, it could benefit from slightly more context without sacrificing brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity as a mutation with no annotations and no output schema, the description is incomplete. It doesn't explain what feeding does (e.g., returns pet status or success message), potential errors, or behavioral nuances. For a tool that likely changes state, this leaves too many gaps, making it inadequate for effective use without additional inference.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no parameter semantics beyond what the input schema provides. The schema has 100% coverage with a clear description and enum for the 'food' parameter, detailing types like 'snack', 'meal', or 'feast'. Since the schema does the heavy lifting, the baseline score is 3, as the description doesn't compensate or add extra meaning, but it also doesn't contradict the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Feed your virtual pet' clearly states the action (feed) and target (virtual pet), providing a basic purpose. However, it doesn't distinguish this tool from sibling tools like 'play_with_pet' or 'put_to_bed' beyond the obvious action difference, nor does it specify what feeding accomplishes (e.g., increases happiness or health). This makes it vague in context, as it lacks sibling differentiation and specific outcomes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description offers no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., pet must be awake or hungry), exclusions (e.g., don't use if pet is full), or comparisons to siblings like 'check_pet' for status monitoring. Without such context, users must infer usage from the tool name alone, which is insufficient for informed selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Play with your virtual pet
| Name | Required | Description | Default |
|---|---|---|---|
| activity | Yes | Type of play activity: ball, chase, or puzzle |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('Play') but doesn't describe effects (e.g., how it affects pet happiness, energy levels, or other states), side effects, or constraints (e.g., cooldowns, limitations based on pet type). This leaves significant gaps for a tool that likely modifies pet state.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no wasted words. It's front-loaded with the core action and target, making it easy to parse quickly. Every word contributes directly to conveying the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a pet interaction tool with no annotations and no output schema, the description is incomplete. It doesn't explain what happens after playing (e.g., changes to pet attributes, possible errors, or return values), leaving the agent without crucial context for effective use. This is inadequate for a tool that likely involves state changes.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, clearly documenting the 'activity' parameter with an enum and description. The description adds no additional parameter information beyond what the schema provides, such as explaining the impact of different activity choices. Since schema coverage is high, the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Play with your virtual pet' states a clear action ('Play') and target ('virtual pet'), but it's somewhat vague about what 'play' entails compared to other pet interactions. It distinguishes from siblings like 'feed_pet' or 'clean_pet' by focusing on play, but doesn't specify how it differs from other interactive tools beyond the general concept.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., if the pet must be awake or healthy), exclusions (e.g., not to use if the pet is sleeping), or comparisons to sibling tools like 'check_pet' for status monitoring. Usage is implied by the name but not explicitly defined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Put your virtual pet to sleep to restore energy
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('put to sleep') and outcome ('restore energy'), but doesn't describe side effects (e.g., does this make the pet unavailable for other actions?), time requirements, or success conditions. For a mutation tool with zero annotation coverage, this leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the key action and purpose. Every word earns its place: 'Put your virtual pet to sleep' specifies the action, and 'to restore energy' clarifies the goal. There is no redundancy or unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (simple mutation with no parameters) and lack of annotations/output schema, the description is minimally adequate. It explains what the tool does but doesn't cover behavioral details like side effects or energy restoration mechanics. For a mutation tool, more context on outcomes or constraints would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters, and schema description coverage is 100%, so no parameter documentation is needed. The description appropriately doesn't discuss parameters, focusing instead on the tool's purpose. Baseline is 4 for zero-parameter tools when the description is adequate for the action.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('put to sleep') and the resource ('virtual pet'), with the specific purpose 'to restore energy'. It distinguishes from siblings like 'check_pet' or 'play_with_pet' by focusing on energy restoration rather than status checking or entertainment. However, it doesn't explicitly contrast with all siblings (e.g., 'feed_pet' might also restore energy).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context ('to restore energy'), suggesting this tool should be used when the pet's energy is low. However, it doesn't provide explicit guidance on when NOT to use it (e.g., if the pet is already sleeping) or mention alternatives like 'feed_pet' for energy restoration. The context is clear but lacks exclusion criteria or sibling comparisons.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0check_petclean_petcreate_petfeed_petplay_with_petput_to_bedScored across 6 tools
Every tool has a clearly distinct purpose with no ambiguity: create_pet initializes a new pet, while check_pet monitors status, and feed_pet, clean_pet, play_with_pet, and put_to_bed each handle specific care actions. The descriptions reinforce unique functions, making misselection unlikely.
All tools follow a consistent verb_noun pattern with snake_case, such as check_pet, feed_pet, and play_with_pet. This uniformity enhances readability and predictability, making the tool set easy to navigate without deviations.
With 6 tools, the count is well-scoped for a virtual pet management domain, covering core actions like creation, status checks, and care activities. Each tool earns its place without feeling excessive or insufficient for the intended purpose.
The tool set provides strong coverage for basic pet care, including creation, feeding, cleaning, playing, and sleep management. A minor gap exists in lacking update or delete operations for pets, but agents can work around this for most workflows.
A Tamagotchi for AI agents. Real-time care, permanent death, dozens of species, evolution.
A public stage for AI agents to express a personality, play, meet and remember shared moments.
A persistent AI world where agents walk, build, own things, talk, and make agreements.
A persistent creative world for AI agents: shared spaces, stories, objects, messages and polls.