How to Use the Goldsky (Web3 Data Indexing & Subgraphs) MCP in Google ADK

Q: How do I register the Goldsky (Web3 Data Indexing & Subgraphs) MCP Server with the Google ADK?

Initialize McpToolset using the streamable HTTP server parameters pointing to your Vinkius URL. Pass this toolset to your LlmAgent to expose tools like getpipeline to Gemini.

Q: Can I limit which tools the Google ADK agent can access on Goldsky (Web3 Data Indexing & Subgraphs)?

Yes, you can use the toolnames filter when instantiating your toolset. This restricts the agent to read-only tools like getpipelinestatus and blocks destructive actions like deletepipeline.

Q: How does Gemini use Goldsky (Web3 Data Indexing & Subgraphs) to manage subgraphs?

Gemini calls getpipelinestate via the MCP Server to understand the internal progress of your indexers. It uses this state data to coordinate downstream ETL tasks within your Google Cloud infrastructure.

Q: What happens if a pipeline deployment fails validation?

The validatepipeline tool returns specific syntax and schema errors to your agent. The agent can then rewrite the pipeline definition and retry the deployment programmatically.

Connect Gemini models to your Web3 indexing pipelines via this MCP Server and Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Goldsky (Web3 Data Indexing & Subgraphs) MCP to Google ADK

Create your Vinkius account to connect Goldsky (Web3 Data Indexing & Subgraphs) to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Goldsky (Web3 Data Indexing & Subgraphs) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control Goldsky pipelines inside Google ADK

The `create_pipeline` tool allows Gemini agents to provision indexing infrastructure that feeds raw blockchain data directly into your cloud environment. This setup connects live on-chain events to your analytical storage. Your agent uses `list_pipelines` to catalog your active indexers. This MCP integration maps their outputs directly to BigQuery datasets.

Monitor and restart failing subgraphs

The `get_pipeline_status` tool delivers immediate runtime states to your Google ADK agent. When a pipeline halts due to RPC instability, the agent detects the failure instantly. The agent then invokes `restart_pipeline` or `resume_pipeline` to recover the indexing loop. This automated self-healing keeps your analytical dashboards populated with fresh Web3 data.

Analyze pipeline logs using long-context models

The `get_pipeline_logs` tool extracts raw execution traces from your active indexers. Your agent feeds these logs into Gemini's long-context window to diagnose complex smart contract indexing issues. By analyzing outputs from `get_pipeline_error_count` alongside the logs, the agent pinpoints exact block numbers causing ingestion failures. This speeds up debugging for complex DeFi protocol events.

Setup guide

Set up Goldsky (Web3 Data Indexing & Subgraphs) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Goldsky (Web3 Data Indexing & Subgraphs) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Goldsky (Web3 Data Indexing & Subgraphs)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Goldsky (Web3 Data Indexing & Subgraphs) tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Goldsky. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Goldsky (Web3 Data Indexing & Subgraphs) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Goldsky (Web3 Data Indexing & Subgraphs) MCP in Google ADK

Initialize `McpToolset` using the streamable HTTP server parameters pointing to your Vinkius URL. Pass this toolset to your `LlmAgent` to expose tools like `get_pipeline` to Gemini.

Yes, you can use the `tool_names` filter when instantiating your toolset. This restricts the agent to read-only tools like `get_pipeline_status` and blocks destructive actions like `delete_pipeline`.

Gemini calls `get_pipeline_state` via the MCP Server to understand the internal progress of your indexers. It uses this state data to coordinate downstream ETL tasks within your Google Cloud infrastructure.

The `validate_pipeline` tool returns specific syntax and schema errors to your agent. The agent can then rewrite the pipeline definition and retry the deployment programmatically.

All pipeline definitions and connection parameters are transmitted via encrypted transport to isolated execution environments. Your private RPC endpoints and database credentials are never persisted outside your secure session.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript