TypeScriptベースのModel Context Protocol（MCP）サーバーは、開発者とAI間のインテリジェントな機能に関する議論を促進します。このサーバーはAIリード開発者として機能し、機能実装に関するガイダンスを提供し、議論のコンテキストを維持し、チームが情報に基づいたアーキテクチャ上の意思決定を行うのを支援します。
このサーバーは以下を提供します:
機能の実装とアーキテクチャに関するインタラクティブなディスカッション
機能に関する議論と決定の永続的な記憶
開発アプローチとベストプラクティスに関するインテリジェントなガイダンス
プロジェクト履歴に基づいたコンテキスト認識の推奨事項
機能要件に関する自然な議論に参加する
実装アプローチに関する専門家のガイダンスを受ける
建築に関する推奨事項を受け取る
複数の議論にわたって文脈を維持する
機能に関する議論の永続的な保存
機能の進化と決定を追跡する
文脈については以前の議論を参照する
リンク関連の機能と依存関係
ベストプラクティスの推奨事項
実装戦略の提案
アーキテクチャパターンの推奨事項
テクノロジースタックの考慮事項
プロジェクト全体の機能コンテキストを維持する
機能間の依存関係を追跡する
店舗のアーキテクチャ上の決定
前回の議論の結果を思い出す
Related MCP server: Context Management System
Claude 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": {
"feature-discussion": {
"command": "/path/to/feature-discussion/build/index.js"
}
}
}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 watchMCP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。パッケージスクリプトとして提供されているMCP Inspectorの使用をお勧めします。
npm run inspectorインスペクターは、ブラウザでデバッグ ツールにアクセスするための URL を提供します。
貢献を歓迎します！開始方法の詳細については貢献ガイドラインを、コミュニティのガイドラインについては行動規範をご覧ください。
このプロジェクトは MIT ライセンスに基づいてライセンスされています - 詳細についてはLICENSEファイルを参照してください。
Start a new feature discussion
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Title or name of the feature |
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. 'Start a new feature discussion' implies a creation/mutation operation, but it doesn't specify permissions needed, whether this is reversible, what happens after starting, or any rate limits. It lacks crucial context for safe and effective use.
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 zero wasted words. It's appropriately sized for a simple tool and front-loads the core purpose immediately.
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 no annotations, no output schema, and a mutation tool with behavioral gaps, the description is incomplete. It doesn't explain what 'starting a feature discussion' entails, what the result looks like, or how it relates to the sibling tool. More context is needed for effective 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?
Schema description coverage is 100%, so the schema already documents the single 'title' parameter. The description adds no additional meaning about parameters beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.
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 'Start a new feature discussion' clearly indicates the action (start) and resource (feature discussion), but it's somewhat vague about what this entails. It doesn't specify what a 'feature discussion' is in this context or how it differs from the sibling tool 'provide_feature_input'.
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 the sibling 'provide_feature_input'. There's no mention of prerequisites, context, or alternatives. The user 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.
Provide information for the current feature discussion prompt
| Name | Required | Description | Default |
|---|---|---|---|
| featureId | Yes | ID of the feature being discussed | |
| response | Yes | Your response to the current prompt |
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. It mentions 'provide information', which suggests a read or input operation, but doesn't clarify if this is a mutation, requires specific permissions, has side effects, or details the response format. For a tool with zero annotation coverage, this is a significant gap in transparency.
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 unnecessary words. It is front-loaded and appropriately sized for its function, making it highly concise and well-structured.
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 lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns, how it interacts with the sibling tool 'begin_feature_discussion', or provide behavioral details. For a tool with two required parameters and no structured support, the description should offer more context to guide the agent 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 schema description coverage is 100%, with clear descriptions for both parameters ('featureId' and 'response'). The description adds no additional meaning beyond what the schema provides, such as explaining the context or format of 'response'. Given the high schema coverage, the baseline score of 3 is appropriate, as the schema handles the parameter documentation adequately.
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 'Provide information for the current feature discussion prompt', which is clear but vague. It specifies the action ('provide information') and context ('current feature discussion prompt'), but doesn't clarify what type of information or how it differs from the sibling tool 'begin_feature_discussion'. This makes it adequate but with room for improvement.
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, such as the sibling tool 'begin_feature_discussion'. It implies usage in the context of a 'current feature discussion prompt', but lacks explicit instructions on prerequisites, timing, or comparisons to other tools, leaving the agent with minimal direction.
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.
begin_feature_discussionprovide_feature_inputScored across 2 tools
The two tools have clearly distinct purposes: 'begin_feature_discussion' initiates a new discussion, while 'provide_feature_input' adds information to an existing one. There is no overlap in functionality, making it impossible for an agent to confuse them.
Both tools follow a consistent verb_noun pattern with snake_case naming. 'begin_feature_discussion' and 'provide_feature_input' use clear, descriptive verbs ('begin' and 'provide') paired with the same noun phrase ('feature_discussion' or 'feature_input'), ensuring predictability.
With only 2 tools, the server feels thin for a feature discussion domain. It lacks essential operations like retrieving, updating, or closing discussions, which limits its utility and suggests an incomplete scope.
The tool surface is severely incomplete for feature discussions. It covers starting a discussion and providing input, but missing critical operations such as getting discussion details, listing discussions, updating status, or adding comments, which will likely cause agent failures in real workflows.
AI colleagues that keep your standards, your project and their reasoning between sessions
Capture feature requests and bug reports from chat into a searchable, AI-categorized backlog.
Generate architecture docs, implementation plans, and dev tickets from your project requirements.
Bring your saved preferences, project decisions, and useful context into your next AI conversation.
