How to Use the Glassnode (On-chain Data) MCP in OpenAI Agents SDK

Q: How do I connect the Glassnode (On-chain Data) MCP Server to my OpenAI Agents SDK pipeline?

Install the package using pip install openai-agents and initialize the server stream using MCPServerStreamableHttp with your Vinkius URL. Pass this instance inside the mcpservers list when creating your Agent. The SDK auto-discovers the tools and exposes them to your model instantly.

Q: Does this setup support caching for frequent metric requests?

Yes, setting cacheToolsList=True in your SDK configuration prevents redundant schema fetches. For actual data points from getmetric, you should implement a simple redis cache or rely on Vinkius's edge caching to avoid burning your API credits.

Feed live Glassnode on-chain metrics directly to your OpenAI Agents SDK workflow with zero-config tool discovery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Glassnode (On-chain Data) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Glassnode (On-chain Data) 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 Glassnode (On-chain Data) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time market state querying for agents

The `get_metric` tool exposes direct time-series data for active addresses, transaction counts, and exchange balances straight to your agent. When your agent runs a quantitative strategy, it calls this endpoint to pull exact numbers for assets like Bitcoin or Ethereum without manual API parsing. You pass the server to your agent constructor, and the model decides when to pull these metrics based on user prompts. The OpenAI Agents SDK handles the tool schema mapping behind the scenes, so your agent knows exactly what parameters to send.

Bulk data ingestion with built-in guardrails

The `get_bulk_metric` tool pulls multi-asset datasets in a single request to feed raw market data into your trading models. This tool accepts a wildcard asset parameter to retrieve data across hundreds of tokens simultaneously, cutting down network roundtrips. Because the OpenAI Agents SDK validates agent actions before they execute on the Vinkius platform, you prevent your agent from making runaway API calls. This safety barrier ensures your Glassnode API limits remain intact during high-volatility events.

Point-in-time backtesting using the MCP Server

The `get_pit_metric` tool delivers historical snapshots to eliminate look-ahead bias during agent-led backtesting. Your agent uses this tool to query what the market looked like at a precise block height or timestamp, ensuring realistic strategy simulation. Integrating this MCP Server with the OpenAI Agents SDK lets you run multi-agent pipelines where one agent fetches historical data while another evaluates risk. The SDK handles tracing on the OpenAI dashboard, giving you a clear view of every metric requested during a run.

Setup guide

Set up Glassnode (On-chain Data) 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 Glassnode (On-chain Data) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Glassnode (On-chain Data) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Glassnode (On-chain Data) 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="Glassnode (On-chain Data) Agent",
            instructions="You have access to Glassnode (On-chain Data) 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 Glassnode. 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 Glassnode (On-chain Data) 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 Glassnode (On-chain Data) MCP in OpenAI Agents SDK

Install the package using `pip install openai-agents` and initialize the server stream using `MCPServerStreamableHttp` with your Vinkius URL. Pass this instance inside the `mcp_servers` list when creating your Agent. The SDK auto-discovers the tools and exposes them to your model instantly.

Yes, you can filter the exposed tools during the initialization step or manage access directly in your Vinkius dashboard. This keeps your agent focused on specific operations like `list_assets` or `get_metric` instead of the entire suite.

The SDK lets you configure client-side throttling, while Vinkius manages connection pooling. If your agent spams `get_bulk_metric` calls, the SDK catches rate limit errors gracefully, allowing your agent to back off and retry.

Yes, setting `cacheToolsList=True` in your SDK configuration prevents redundant schema fetches. For actual data points from `get_metric`, you should implement a simple redis cache or rely on Vinkius's edge caching to avoid burning your API credits.

Your Glassnode API keys are stored as encrypted environment variables inside the secure, zero-trust Vinkius V8 sandbox. The MCP Server only exposes the clean tool interfaces like `list_metrics` to your OpenAI agent, meaning the raw API key never leaves the secure execution environment.

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