How to Use the Goldsky (Web3 Data Indexing & Subgraphs) MCP in OpenAI Agents SDK

Q: How do I connect the Goldsky (Web3 Data Indexing & Subgraphs) MCP Server to the OpenAI Agents SDK?

Install openai-agents and initialize the server using the MCPServerStreamableHttp client with your Vinkius endpoint. Pass the server instance directly into your agent constructor to auto-discover all 12 indexing tools.

Q: Can my agent handle pipeline failures automatically using Goldsky (Web3 Data Indexing & Subgraphs) and OpenAI Agents SDK?

Yes, your agent can poll getpipelineerrorcount to detect issues. If errors spike, the agent triggers restartpipeline to restore the indexing flow without manual intervention.

Q: How do I verify a pipeline configuration before deploying it?

Use the validatepipeline tool within your agent's execution loop. This parses your subgraph or pipeline YAML and returns validation errors before you commit to creating resources.

Deploy and monitor Web3 indexing pipelines using this MCP Server with OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Goldsky (Web3 Data Indexing & Subgraphs) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy Web3 pipelines using OpenAI Agents SDK

The `validate_pipeline` tool lets your agent check your YAML configurations before deploying them to Goldsky. This prevents broken deployments by catching schema mismatches and syntax errors before they hit production. Once validated, the agent runs `create_pipeline` to spin up the indexing infrastructure. You get instant feedback on deployment status without leaving your Python runtime.

Inspect live pipeline health and execution logs

The `get_pipeline_status` tool retrieves the current operational state of your active indexers. Your agent uses this MCP tool to monitor whether the ingestion is running, paused, or failing, allowing it to make autonomous recovery decisions. For deep debugging, the agent calls `get_pipeline_logs` and `get_pipeline_error_count` to isolate transient RPC failures or database write errors. This keeps your indexing layer transparent and easy to debug.

Pause, resume, and restart indexers programmatically

The `pause_pipeline` tool stops active indexing when you need to perform database maintenance or schema updates. Your agent controls the state machine of your Web3 data flow dynamically. When maintenance finishes, the agent uses `resume_pipeline` or `restart_pipeline` to bring the indexer back online. This eliminates manual CLI commands and keeps your data pipelines synchronized.

Setup guide

Set up Goldsky (Web3 Data Indexing & Subgraphs) MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Goldsky (Web3 Data Indexing & Subgraphs) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Goldsky (Web3 Data Indexing & Subgraphs) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Goldsky (Web3 Data Indexing & Subgraphs) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Goldsky (Web3 Data Indexing & Subgraphs) Agent",
            instructions="You have access to Goldsky (Web3 Data Indexing & Subgraphs) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` and initialize the server using the `MCPServerStreamableHttp` client with your Vinkius endpoint. Pass the server instance directly into your agent constructor to auto-discover all 12 indexing tools.

Yes, your agent can poll `get_pipeline_error_count` to detect issues. If errors spike, the agent triggers `restart_pipeline` to restore the indexing flow without manual intervention.

The SDK queries the MCP Server endpoint at runtime to fetch the schema for tools like `list_pipelines`. Enable `cacheToolsList=True` to speed up subsequent agent runs and reduce network overhead.

Use the `validate_pipeline` tool within your agent's execution loop. This parses your subgraph or pipeline YAML and returns validation errors before you commit to creating resources.

Your pipeline configurations and API keys are processed in an ephemeral, zero-trust V8 sandbox. No database credentials or raw blockchain event schemas are stored on the host, ensuring your infrastructure access remains isolated.

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