Goldsky Docs

npx add-mcp 'https://docs.goldsky.com/mcp'

Goldsky MCP Server

Connect Claude, Cursor, and other MCP clients to the hosted Goldsky MCP server so they can search docs for Subgraphs, Turbo, Edge RPC, Compose, and Feeds.

About the Goldsky MCP server

The Model Context Protocol (MCP) is an open standard for connecting AI applications to external services. Goldsky hosts an MCP server so AI tools like Claude, Cursor, and other MCP clients can search our documentation directly:

• Find relevant documentation while coding
• Get accurate answers about Goldsky's capabilities
• Pull examples into your editor's context
• Navigate between related features across products

How the Goldsky MCP server works

When an AI tool has the Goldsky MCP server connected, it can search our documentation while generating a response:

• The AI searches Goldsky docs when relevant to your question
• Searches span all core Goldsky products (Subgraphs, Turbo, Edge RPC, Boost, Feeds, and Compose)
• Results come from the live docs, so answers stay current

Access the Goldsky MCP server

The Goldsky MCP server is hosted at:

https://docs.goldsky.com/mcp

Connect the Goldsky MCP server

Choose your preferred AI tool to get started with the Goldsky MCP server:

Cursor

To connect the Goldsky MCP server to Cursor:

1. Open MCP settings

1. Use Command + Shift + P (Ctrl + Shift + P on Windows) to open the command palette.
2. Search for "Open MCP settings".
3. Select Add custom MCP. This opens the mcp.json file.

2. Configure the Goldsky MCP server

In mcp.json, add the Goldsky server:

{
  "mcpServers": {
    "Goldsky": {
      "url": "https://docs.goldsky.com/mcp"
    }
  }
}

3. Test the connection

In Cursor's chat, ask "What tools do you have available?" Cursor should show the Goldsky MCP server as an available tool.

[!TIP]

Try asking: "How do I deploy a subgraph on Goldsky?" or "What data sinks does Turbo support?"

See the Cursor documentation for more details.

VS Code

To connect the Goldsky MCP server to VS Code:

1. Create MCP configuration

1. Create a .vscode/mcp.json file in your project root.
2. In mcp.json, configure the Goldsky server:

{
  "servers": {
    "Goldsky": {
      "type": "http",
      "url": "https://docs.goldsky.com/mcp"
    }
  }
}

2. Restart VS Code

Restart VS Code to load the MCP configuration.

3. Verify the connection

Use GitHub Copilot Chat and ask about Goldsky features. The AI should be able to access Goldsky documentation through the MCP server.

[!TIP]

Try asking: "Show me how to create a Turbo pipeline" or "What's the difference between Subgraphs and Turbo?"

See the VS Code documentation for more details.

Claude

To use the Goldsky MCP server with Claude:

1. Add the Goldsky MCP server to Claude

1. Navigate to the Connectors page in Claude settings.
2. Select Add custom connector.
3. Add the Goldsky MCP server:
   • Name: Goldsky
   • URL: https://docs.goldsky.com/mcp
4. Select Add.

2. Access the MCP server in your chat

1. When using Claude, select the attachments button (the plus icon).
2. Select the Goldsky MCP server.
3. Ask Claude questions about Goldsky.

[!TIP]

Try asking: "How do I migrate a Mirror pipeline to Turbo?" or "Show me examples of Compose task triggers"

See the Model Context Protocol documentation for more details.

Claude Code

To use the Goldsky MCP server with Claude Code, run the following command:

claude mcp add --transport http Goldsky https://docs.goldsky.com/mcp

Test the connection by running:

claude mcp list

[!TIP]

Verify that "Goldsky" appears in the list of available MCP servers.

See the Claude Code documentation for more details.

Agent skills for AI coding assistants

Beyond documentation search, Goldsky provides Agent Skills: workflow-based skills that guide AI assistants through tasks like deploying pipelines, managing secrets, and debugging issues.

See the AI agent skills page for installation instructions and available skills.

Using the Goldsky MCP server effectively

Best practices for AI-assisted development

Once connected, your AI assistant can help you with:

Product selection and architecture

When to use: Starting a new project or evaluating options

Ask questions like:

• "Should I use Subgraphs or Turbo for my NFT marketplace?"
• "When should I choose Turbo over Subgraphs?"

The AI will search across product documentation to provide comparative guidance.

Configuration and setup

When to use: Setting up pipelines, subgraphs, or compose apps

Ask questions like:

• "Show me a Turbo pipeline config for decoding Uniswap events"
• "How do I configure a Turbo pipeline with TypeScript transforms?"
• "What's the syntax for Compose task triggers on ERC-20 transfers?"

The AI will find relevant configuration examples and syntax.

Troubleshooting and debugging

When to use: Fixing issues or understanding errors

Ask questions like:

• "My subgraph deployment failed with error X, what does this mean?"
• "How do I debug a failing Turbo transform?"
• "What are common issues with Compose task execution?"

The AI will search documentation for error explanations and solutions. If it can't help, email our support team and mention that you're using the MCP server for priority support. We keep adding debugging guidance to the docs to improve MCP results.

Product-specific search tips

Subgraphs

Key topics to search:

• Deploying and managing subgraphs
• GraphQL schema and queries
• Instant subgraphs (no-code)
• Cross-chain/multi-chain indexing
• Webhooks and event notifications
• Migration from The Graph or Alchemy

Example queries:

• "How do I create an instant subgraph?"
• "Show me how to deploy a cross-chain subgraph"
• "What's the webhook payload format?"

Edge RPC

Key topics to search:

• JSON-RPC method reference (eth_*, debug_*, trace_*)
• Endpoint setup and authentication
• Rate limits and transport options
• Error codes
• Capabilities (Flashblocks, x402)

Example queries:

• "What parameters does eth_getLogs take?"
• "Show me the Edge RPC endpoint format for Base"
• "What Edge RPC error codes mean I'm rate limited?"

Turbo

Key topics to search:

• Pipeline configuration syntax
• TypeScript transform syntax
• Data sources (EVM, Solana, Stellar)
• Dynamic tables and schemas
• HTTP handlers and webhooks
• Job mode vs streaming mode

Example queries:

• "Show me TypeScript transform examples"
• "How do I configure Solana source in Turbo?"
• "What's the syntax for dynamic table definitions?"

Compose

Key topics to search:

• Task authoring and structure
• Task triggers (time-based, blockchain events)
• Context functions (fetch, EVM, collections)
• Environment variables and secrets
• Deployment and monitoring
• Package imports

Example queries:

• "How do I create a task triggered by contract events?"
• "Show me how to use EVM context to read contract state"
• "How do I deploy and monitor Compose apps?"

[!TIP]

Be specific about products: mention the Goldsky product you mean (Subgraphs, Turbo, Edge RPC, or Compose) to get more targeted results.

Example: "How do I configure a Turbo pipeline?" vs "How do I configure a pipeline?" (ambiguous between products)

Related topics

• Build with agents
• Agent Skills
• Introduction to Goldsky
• Get started with Feeds
• Frequently asked questions