Goldsky MCP Server

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, 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
VS Code
Claude
Claude Code

To connect the Goldsky MCP server to Cursor:

Open MCP settings

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

Configure the Goldsky MCP server

In mcp.json, add the Goldsky server:

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

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.

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

See the Cursor documentation for more details.

To connect the Goldsky MCP server to VS Code:

Create MCP configuration

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

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

Restart VS Code

Restart VS Code to load the MCP configuration.

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.

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.

To use the Goldsky MCP server with Claude:

Add the Goldsky MCP server to Claude

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

Access the MCP server in your chat

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

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.

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

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 optionsAsk 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 appsAsk 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 errorsAsk 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
Edge RPC
Turbo
Compose

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?”

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?”

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)

Get started

Solutions

Account & billing

Security & operations

Resources

About the Goldsky MCP server

How the Goldsky MCP server works

Access the Goldsky MCP server

Connect the Goldsky MCP server

Agent skills for AI coding assistants

Using the Goldsky MCP server effectively

Best practices for AI-assisted development

Product-specific search tips

​About the Goldsky MCP server

​How the Goldsky MCP server works

​Access the Goldsky MCP server

​Connect the Goldsky MCP server

​Agent skills for AI coding assistants

​Using the Goldsky MCP server effectively

​Best practices for AI-assisted development

​Product-specific search tips

About the Goldsky MCP server

How the Goldsky MCP server works

Access the Goldsky MCP server

Connect the Goldsky MCP server

Agent skills for AI coding assistants

Using the Goldsky MCP server effectively

Best practices for AI-assisted development

Product-specific search tips