Token Counter and Budget EnforcerをAIに接続

最速日

718ms

最遅日

937ms

14日間の傾向

遅延傾向+15%

Token Counter and Budget Enforcer Connector

準備完了です。MCPクライアントを選択し、セットアップ手順に従ってください。

コネクタリンクhttps://edge.vinkius.com/vk_preview_Fntor1z8zuXrJce6K2HdextT8uXupjEA6h8NsXAn/mcpコピー

Claude Desktop

以下の手順で数秒で接続できます。

1. 1In Claude Desktop, open Settings → Connectors.
2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3. 3Click Add and start a new chat — Token Counter and Budget Enforcer capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "token-counter-and-budget-enforcer-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_Fntor1z8zuXrJce6K2HdextT8uXupjEA6h8NsXAn/mcp"
    }
  }
}

• Claude
• ChatGPT
• Cursor
• VS Code
• Windsurf
• Claude Code
• JetBrains
• Cline

各クライアントの手順ガイドはこちらです。 接続方法

Claude向けのガイド付きセットアップ？ Token Counter and Budget EnforcerをClaudeや他のAIに設定する

このConnectorが対応するすべてのAIクライアントを見る ↑

• 01

  AIエンジニア

  エージェントのトークン消費を正確に把握し、リソース管理を最適化したい開発者。

• 02

  MLOpsエンジニア

  LLMの運用コストを監視し、予算に基づいた厳格な制御を行いたい運用担当者。

• 03

  プロダクトマネージャー

  AIサービスのコスト構造を可視化し、予算内での安定した運用を目指す責任者。

• 01

  How does this MCP estimate tokens?

  It uses deterministic BPE approximation to calculate token counts for both text and code.

• 02

  Can I set different limits for different agents?

  Yes, the MCP tracks cumulative usage per agent, allowing you to enforce unique limits for each one.

• 03

  Does checking the usage summary cost tokens?

  No, the get_usage_summary capability retrieves current totals without consuming any new tokens.

• 04

  How does it prevent budget overruns?

  The track_and_enforce_usage capability updates usage and checks it against your set limits to stop spending once a cap is reached.

• 05

  Which AI clients can use this MCP?

  Any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

• 06

  How are tokens estimated?

  Tokens are estimated using a deterministic character-to-token ratio: approximately 4 characters per token for English text and 3.5 characters per token for code blocks.

• 07

  Can I set different limits for agents and conversations?

  Yes. You can use track_and_enforce_usage to apply specific limits for both the unique agent identifier and the specific conversation identifier.

• 08

  How do I check my current usage?

  You can use the get_usage_summary capability to retrieve the cumulative token totals for a specific agent or conversation without consuming any new tokens.

• 

  Langfuse (LLM Tracing & Evals) AIコネクタ

  Monitor LLM apps via Langfuse — track traces, manage prompt templates, and audit evaluation scores.

  表示
• 

  LLM Token Counter AIコネクタ

  Calculate exact and estimated token counts for GPT-4, GPT-4o, Claude, and Llama models.

  表示
• 

  LLM API Cost Estimator AIコネクタ

  Calculate exact API costs and track session budgets for LLM workflows.

  表示
• 

  New Relic AI (LLM Observability) AIコネクタ

  Monitor and audit LLM telemetry via New Relic AI — track token costs, p95 latency, and user feedback.

  表示

おすすめ

• 

  LLM API Cost Calculator AIコネクタ

  Estimate and compare the financial impact of LLM usage across different providers.

  表示
• 

  LLM Context Window Budgeter AIコネクタ

  Monitor and predict LLM context window exhaustion with precision token forecasting.

  表示
• 

  Datadog AI (LLM Observability) AIコネクタ

  Monitor LLM performance via Datadog — track token usage, audit prompts, and monitor AI model metrics directly

  表示
• 

  Token Count Estimator AIコネクタ

  Deterministic LLM token estimation using character-based heuristics.

  表示