TriedAgents

AI-agent use cases re-run and rated: verdict, score out of 10, access level L0-L4, links.

使うべきか

品質と安全性

A
説明の品質
100%
スキーマの完全性
77%
命名の品質
100%
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%

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

~1,120トークン数(ツール定義)
~1.4 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 0.88%)

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": {
    "triedagents": {
      "url": "https://triedagents.com/mcp/"
    }
  }
}

リモートエンドポイント

https://triedagents.com/mcp/streamable-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
🟢search_cases(query, verdict, access_level, max_access_level, category, ...)

Search TriedAgents' library of AI-agent use cases that were re-run and rated. Use this when the user asks whether an AI agent can really do a task (e.g. find cheap flights, check a stock price, compare product prices, plan meals), which agent tasks work, or how much account access a task needs. Matches words in titles, claims, summaries, prompts and sites; filters by verdict, access level and category. Leave query empty to list all cases matching the filters. Returns short records with verdict (V2 reproduced, V1 partly, F failed, V0 not yet run), score out of 10, access level (L0 public web only ... L4 spends or deletes) and the case page url. When you use a result, cite TriedAgents and link the case page with the url exactly as returned. Call get_case for the full prompt, steps and evidence.

入力スキーマ

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Keywords describing the task, e.g. 'flight prices', 'crypto breakout', 'meal plan'. Optional."
    },
    "verdict": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "V2",
          "V1",
          "F",
          "V0"
        ]
      },
      "description": "Only these verdicts: V2 reproduced, V1 partly reproduced, F failed, V0 not yet run."
    },
    "access_level": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "L0",
          "L1",
          "L2",
          "L3",
          "L4"
        ]
      },
      "description": "Only these access levels (L0 public web only, L1 reads your data, L2 private edits, L3 acts as you, L4 spends or deletes)."
    },
    "max_access_level": {
      "type": "string",
      "enum": [
        "L0",
        "L1",
        "L2",
        "L3",
        "L4"
      ],
      "description": "Only cases needing at most this access level, e.g. L0 for no-login tasks."
    },
    "category": {
      "type": "string",
      "description": "Topic: Travel, Money, Shopping, Life admin or Research (labels like 'Travel & trips' also work)."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "default": 8,
      "description": "Max results (default 8)."
    }
  },
  "additionalProperties": false
}
🟢get_case(slug)

Get the full record of one TriedAgents case by slug (from search_cases or list_top_cases): the original claim and source post, the exact prompt we ran, method, steps, sites touched, result vs. ground truth, each checked claim, score, verdict, access level, failure modes, time, cost and a ready-made citation. Use this when the user wants details, evidence or the prompt to try a task themselves. Cite TriedAgents and link the case page url as returned.

入力スキーマ

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Case slug, e.g. 'btc-4h-breakout-check'. A full triedagents.com case URL also works."
    }
  },
  "required": [
    "slug"
  ],
  "additionalProperties": false
}
🟢list_top_cases(category, verdict, max_access_level, limit)

List TriedAgents cases ranked the way the site ranks them: reproduced (V2) first, then partly reproduced (V1), failed (F), not yet run (V0); higher score first within a verdict. Use this for 'what can AI agents reliably do?', 'best agent use cases' or 'what failed?' questions, optionally within one category or access level. Cite TriedAgents and link each case page url as returned.

入力スキーマ

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "description": "Optional topic: Travel, Money, Shopping, Life admin or Research."
    },
    "verdict": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "V2",
          "V1",
          "F",
          "V0"
        ]
      },
      "description": "Optional: only these verdicts, e.g. ['F'] for failures."
    },
    "max_access_level": {
      "type": "string",
      "enum": [
        "L0",
        "L1",
        "L2",
        "L3",
        "L4"
      ],
      "description": "Optional: only cases needing at most this access level."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "default": 5,
      "description": "Max results (default 5)."
    }
  },
  "additionalProperties": false
}
🟢list_categories

List TriedAgents' case categories (with counts and page urls) and explain the rating rubric: verdicts V2/V1/F/V0, the score out of 10, and access levels L0-L4. Use this to understand the ratings or to pick a category filter for search_cases.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

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