Goldsky Web3 Data Indexing SubgraphsをAIに接続

• 01 / 03subgraphの失敗をデバッグする方法
• 02 / 03パイプラインのデプロイ方法
• 03 / 03パイプラインの管理方法

最速日

738ms

最遅日

1354ms

14日間の傾向

改善傾向-6%

Goldsky 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_vKwCn24rK9jiYRm7bJaactLmNUpPZSSNAnWrQ0l6/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 — Goldsky capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "goldsky-web3-data-indexing-subgraphs-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_vKwCn24rK9jiYRm7bJaactLmNUpPZSSNAnWrQ0l6/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？ Goldsky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

  Web3デベロッパー

  エディタを離れることなく、サブグラフやパイプラインのデプロイとデバッグを行えます。

• 02

  データエンジニア

  インデックスの健全性を監視し、リアルタイムでログを取得してデータフローの問題を解決できます。

• 03

  プロトコルチーム

  自然言語による簡単なコマンドで、クロスチェーンのデータインデックス基盤を管理できます。

• 01

  What AI clients can I use with this Goldsky MCP?

  You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

• 02

  Do I need to host the MCP myself?

  No, Vinkius hosts and manages the MCP for you. You just connect and start using it.

• 03

  Can I delete a pipeline through my AI agent?

  Yes, you can use the delete_pipeline capability to remove a pipeline, but remember this action is irreversible.

• 04

  How do I know if my pipeline is running correctly?

  You can ask your agent to check the pipeline status or query the error count for a specific time window.

• 05

  Can I validate my configuration before I deploy it?

  Yes, the validate_pipeline capability allows your agent to check your definitions for errors before deployment.

• 06

  Can I check if my pipeline configuration is valid before deploying it?

  Yes! Use the validate_pipeline capability with your definition object. It will check your sources, transforms, and sinks for errors without actually starting a new pipeline.

• 07

  How do I monitor errors in a running pipeline?

  You can use get_pipeline_error_count to see the number of issues in a time window, or get_pipeline_logs to fetch the actual execution logs for detailed debugging.

• 08

  Is it possible to temporarily stop a pipeline without deleting it?

  Absolutely. Use the pause_pipeline capability to stop execution. When you are ready to start again, simply use the resume_pipeline capability.

• 

  PubNub (Real-time Messaging) AIコネクタ

  Enable real-time messaging, presence tracking, and message history for your AI agent using PubNub's global dat

  表示
• 

  Sablier (Token Streaming & Real-time Payroll) AIコネクタ

  Manage real-time token streams and airdrop campaigns. Query Sablier indexers, create Merkle trees for distribu

  表示
• 

  Tinybird Data Platform AIコネクタ

  Analyze real-time data via Tinybird — manage Data Sources, inspect Pipes, and query endpoints directly.

  表示
• 

  Hevo Data (ETL & Data Pipeline) AIコネクタ

  Manage data pipelines via Hevo — list pipelines, monitor destinations, and track usage.

  表示

おすすめ

• 

  QuestDB (Time-Series) AIコネクタ

  High-performance time-series database for fast SQL queries, data ingestion, and real-time analytics directly f

  表示
• 

  Real-Time Currency Exchange AIコネクタ

  Give your AI access to the global forex market. Convert real-time and historical currencies instantly using of

  表示
• 

  Data Pipeline Prover AIコネクタ

  A data team asked an AI to build an ETL pipeline. No schema contract. No idempotency. No freshness SLA. The pi

  表示
• 

  Papertrail (Real-time Cloud Log Manager) AIコネクタ

  Manage and analyze cloud logs in real-time via Papertrail — search events, list systems, and organize log grou

  表示