An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Goldsky Web3 Data Indexing Subgraphs to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Control your blockchain data pipelines through natural language.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 12 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 12 available through Goldsky.

  1. 01

    Get pipeline state

    Fetches the internal state of a pipeline to see exactly how it is behaving.

  2. 02

    Get pipeline status

    Reports the current runtime status, such as whether a pipeline is running, paused, or failed.

  3. 03

    Pause pipeline

    Stops a running pipeline immediately.

  4. 04

    Resume pipeline

    Restarts a pipeline that was previously paused.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 12 available through Goldsky.

  1. 05

    Validate pipeline

    Checks your pipeline definition for errors before you deploy it.

  2. 06

    Create pipeline

    Deploys a brand new pipeline to your Goldsky project.

  3. 07

    Delete pipeline

    Removes a specific pipeline from your Goldsky project permanently.

  4. 08

    Get pipeline error count

    Checks how many errors occurred within a specific time window for a pipeline.

Capability set03 / 03

09-12

4 capabilities in this set.

Part of 12 available through Goldsky.

  1. 09

    Get pipeline logs

    Retrieves the execution logs for a pipeline so your agent can troubleshoot issues.

  2. 10

    Get pipeline

    Returns the full configuration and details for a specific pipeline.

  3. 11

    List pipelines

    Shows a list of all pipelines currently in your Goldsky project.

  4. 12

    Restart pipeline

    Triggers a restart for a pipeline to refresh its execution.

Real work

What teams actually run

01

Rapid Debugging

When a subgraph fails, ask your agent to fetch the logs and error counts immediately.

02

Automated Deployment

Use your agent to validate and deploy new pipeline configurations from your code.

03

Resource Management

Pause specific pipelines during low-activity periods to manage your Goldsky resources.

04

Health Monitoring

Set up your agent to periodically check the status of critical real-time data streams.

Automate a task

Put Goldsky to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Goldsky works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Goldsky to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

966ms average. Fast in production.

Goldsky is checked daily against the live service.

Daily averagePeak 1354ms
Oct 3Today
Fastest day
738ms
Slowest day
1354ms
14-day trend
Improving-6%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 12 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Goldsky, so you can see the experience inside your AI.

It does not authenticate your account with Goldsky. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Goldsky Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_vKwCn24rK9jiYRm7bJaactLmNUpPZSSNAnWrQ0l6/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  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.
Configuration · claude_desktop_config.jsonCopy
{
  "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

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Goldsky in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Goldsky owners hand off.

This MCP is built for technical teams managing high-throughput blockchain data.

  • 01

    Web3 Developers

    They use the agent to deploy and debug subgraphs without leaving their IDE.

  • 02

    Data Engineers

    They monitor indexing health and pull logs to fix data flow issues.

  • 03

    Protocol Teams

    They manage cross-chain indexing infrastructure via conversational commands.

FAQ

Questions Goldsky owners ask.

  • 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.

Explore

More in Developer Tools

Suggestions

Connect Goldsky to Claude, Cursor, ChatGPT & more