How to Use the Glassnode (On-chain Data) MCP in LangChain

Q: How does the agent handle rate limits when pulling heavy metric series?

The agent uses getmetricdetails to check allowed parameters before executing a query. This prevents malformed requests that waste your API quota and trigger rate limits.

Feed institutional on-chain metrics directly into your LangChain reasoning loops to trade using hard, verifiable crypto data.

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 LangChain

Create your Vinkius account to connect Glassnode (On-chain Data) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step chains with raw on-chain data

The `list_metrics` MCP tool lets your agent find exact data paths like active addresses or exchange flows before calling them. By feeding this output directly into the next link of your LangChain pipeline, the agent knows exactly which data points are available for a given token. You don't hardcode paths anymore. The output of one tool automatically configures the input for `get_metric`, allowing your chain to adapt to changing asset metrics on the fly.

Eliminate backtest bias in LangChain agents

The `get_pit_metric` tool delivers Point-in-Time data directly to your agent to stop look-ahead bias during historical runs. This prevents your LangChain sequential chains from evaluating past market states with future knowledge. Your agent gets the exact data state as it existed at that precise block timestamp. This makes backtesting on-chain strategies inside your MCP-enabled chains mathematically honest.

Track global market shifts using this MCP Server

The `get_bulk_metric` tool pulls raw data across thousands of assets simultaneously with a single call. Your LangChain agent processes this bulk payload to identify macro trends across the entire crypto market. By passing this broad dataset to a summary chain, you pinpoint which sectors are gaining momentum. No more querying assets one by one over slow, rate-limited loops.

Setup guide

Set up Glassnode (On-chain Data) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Glassnode (On-chain Data) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "glassnode-on-chain-data-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Glassnode (On-chain Data) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the MCP adapter and initialize the client using your Vinkius endpoint. Call `client.get_tools()` to retrieve the six on-chain tools and pass them directly to your agent's tool list.

Yes, this is where the framework shines. Your agent first calls `list_assets` to verify token support, then feeds that asset ticker directly into `get_metric` to pull the active address count.

LangSmith traces the exact inputs and outputs of tools like `get_bulk_metric`. You see the raw JSON payloads, execution latency, and token consumption for every single on-chain query.

The agent uses `get_metric_details` to check allowed parameters before executing a query. This prevents malformed requests that waste your API quota and trigger rate limits.

Your API key stays in your local environment or secure Vinkius vault. This MCP Server never logs your credentials or exposes your private on-chain query parameters to external parties.

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