Feedback Synthesis MCP

Synthesize GitHub Issues, HN and App Store reviews into ranked pain clusters. Pay-per-call x402.

使うべきか

品質と安全性

A
説明の品質
68%
スキーマの完全性
98%
命名の品質
95%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(3)

  • LOWTool 'synthesize_feedback' description lacks action verbsynthesize_feedback 内
  • LOWTool 'get_pain_points' description lacks action verbget_pain_points 内
  • LOWTool 'get_sentiment_trends' description lacks action verbget_sentiment_trends 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~751トークン数(ツール定義)
~2.0 KB一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 0.59%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "feedback-synthesis-mcp": {
      "command": "uvx",
      "args": [
        "feedback-synthesis-mcp"
      ]
    }
  }
}

実行可能なパッケージ

pypifeedback-synthesis-mcp0.1.1stdio

リモートエンドポイント

https://feedback-synthesis-mcp-production.up.railway.app/mcpstreamable-http

できること

ツール一覧

ツール(4)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
⚪synthesize_feedback(sources, focus, max_items_per_source, since)

Multi-source feedback synthesis into ranked pain clusters.

入力スキーマ

{
  "type": "object",
  "properties": {
    "sources": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "type": "array",
      "description": "List of source configs. Each must have \"type\" (github_issues, hackernews, appstore) and \"target\" (e.g. \"owner/repo\", \"product name\", app ID)."
    },
    "focus": {
      "default": "",
      "type": "string",
      "description": "Optional focus area to prioritize (e.g. \"performance\", \"onboarding\")."
    },
    "max_items_per_source": {
      "default": 100,
      "type": "integer",
      "description": "Max feedback items per source (default 100)."
    },
    "since": {
      "default": "",
      "type": "string",
      "description": "Only include feedback after this date (ISO 8601, e.g. \"2025-01-01\")."
    }
  },
  "required": [
    "sources"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
🟢get_pain_points(source, top_n, max_items)

Quick single-source pain point extraction.

入力スキーマ

{
  "type": "object",
  "properties": {
    "source": {
      "additionalProperties": true,
      "type": "object",
      "description": "Source config with \"type\" (github_issues, hackernews, appstore) and \"target\"."
    },
    "top_n": {
      "default": 10,
      "type": "integer",
      "description": "Number of top pain points to return (default 10)."
    },
    "max_items": {
      "default": 50,
      "type": "integer",
      "description": "Max feedback items to analyze (default 50)."
    }
  },
  "required": [
    "source"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
🟢search_feedback(query, sources, source, target, since, ...)

Full-text search across cached feedback items.

入力スキーマ

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search query string."
    },
    "sources": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional list of source types to filter (e.g. [\"github_issues\"], [\"github\"]).\nAccepted values: github_issues (or \"github\"), hackernews, appstore."
    },
    "source": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Singular alias for sources — accepts a single source type string.\nIf both source and sources are provided, sources takes precedence."
    },
    "target": {
      "default": "",
      "type": "string",
      "description": "Optional target filter (e.g. \"owner/repo\" or app ID)."
    },
    "since": {
      "default": "",
      "type": "string",
      "description": "Only include items after this date (ISO 8601, e.g. \"2025-01-01\")."
    },
    "limit": {
      "default": 20,
      "type": "integer",
      "description": "Max results to return (default 20)."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
🟢get_sentiment_trends(sources, granularity, since)

Time-series sentiment analysis across feedback sources.

入力スキーマ

{
  "type": "object",
  "properties": {
    "sources": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "type": "array",
      "description": "List of source configs. Each must have \"type\" and \"target\"."
    },
    "granularity": {
      "default": "weekly",
      "type": "string",
      "description": "Time granularity — \"weekly\" or \"monthly\" (default \"weekly\")."
    },
    "since": {
      "default": "",
      "type": "string",
      "description": "Only include feedback after this date (ISO 8601)."
    }
  },
  "required": [
    "sources"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 4 件
検証済みバージョンは記録されていませんツール 4 件
検証済みバージョンは記録されていませんツール 4 件