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

Q: How do I convert Glassnode (On-chain Data) tools for LlamaIndex?

Use the llama-index-tools-mcp package to connect to the Vinkius MCP server. Wrap the client in McpToolSpec and call totoollistasync to generate tools compatible with your LlamaIndex agents.

Q: Can I search past Glassnode (On-chain Data) outputs using LlamaIndex RAG?

Yes, by indexing the JSON outputs of tools like getbulkmetric into a vector store. You can then query past on-chain states semantically without re-calling the API.

Q: How do I filter assets in Glassnode (On-chain Data) before indexing with LlamaIndex?

Have your agent run listassets first to build a clean index of supported tokens. This ensures your vector database only contains valid, queryable on-chain assets.

Q: What happens if the agent requests a metric that doesn't exist?

The agent calls getmetricdetails to check the metric's schema and allowed parameters. This self-correcting step prevents ingestion errors in your indexing pipeline.

Index live Glassnode on-chain metrics into your LlamaIndex vector stores to ground your RAG queries in absolute on-chain reality.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index real-time on-chain metrics for RAG

The `get_metric` MCP tool fetches raw time-series data like transaction volumes and close prices directly into your LlamaIndex pipeline. Instead of reading stale reports, your agent indexes this live data directly into a vector store. Your subsequent queries pull from a fresh, structured knowledge base. This keeps your RAG applications grounded in actual on-chain numbers, entirely preventing LLM hallucinations about market states.

Map out available metrics dynamically

The `list_metrics` tool retrieves every active data path on the platform so your indexer knows what is available. LlamaIndex uses this catalog to build a semantic index of available on-chain data types. When you ask a question about exchange flows, the agent queries this index first. It finds the right path and calls `get_metric_details` to understand the query parameters before pulling the data.

Build a historical context engine with this MCP Server

The `get_pit_metric` tool supplies point-in-time historical data to reconstruct past market states for your index. LlamaIndex stores these snapshots to build a chronological knowledge base of market regimes. Your query engine can search through past network congestion events or capitulation phases. This lets you ask complex analytical questions about historical cycles and get answers backed by hard data.

Setup guide

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

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Glassnode (On-chain Data) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Glassnode (On-chain Data) tools.",
)
response = await agent.run("List recent Glassnode (On-chain Data) data")

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 LlamaIndex

Use the `llama-index-tools-mcp` package to connect to the Vinkius MCP server. Wrap the client in `McpToolSpec` and call `to_tool_list_async` to generate tools compatible with your LlamaIndex agents.

Yes, by indexing the JSON outputs of tools like `get_bulk_metric` into a vector store. You can then query past on-chain states semantically without re-calling the API.

Have your agent run `list_assets` first to build a clean index of supported tokens. This ensures your vector database only contains valid, queryable on-chain assets.

The agent calls `get_metric_details` to check the metric's schema and allowed parameters. This self-correcting step prevents ingestion errors in your indexing pipeline.

All data processing runs within a secure, ephemeral V8 isolate on Vinkius. Your query logs, asset lists, and API keys are completely isolated and never stored or shared.

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