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

Q: How do I register Glassnode (On-chain Data) tools in AutoGen?

Import mcpservertools from autogen-extmcp and configure the MCP server URL. Pass the resulting tool list directly to your AssistantAgent constructor to give them on-chain capabilities.

Q: Can AutoGen agents debate the validity of a Glassnode (On-chain Data) metric?

Yes, one agent can call getmetricdetails to verify the exact definition and parameters of a metric. It can then present these details to the group to resolve any analytical disputes.

Q: How do AutoGen agents coordinate when scanning assets with Glassnode (On-chain Data)?

One agent runs listassets to get the master list. It then delegates specific asset chunks to other agents, who query getmetric in parallel to keep the analysis fast.

Q: How does the framework handle complex JSON outputs from bulk queries?

The McpToolAdapter automatically translates the raw JSON outputs into structured formats that AutoGen agents can easily parse, discuss, and act upon.

Let your AutoGen agents debate market regimes using raw Glassnode on-chain data to reach consensus before executing trades.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fuel multi-agent debates with on-chain truth

The `get_metric` MCP tool feeds raw data like active addresses and transaction counts directly into your AutoGen conversation thread. A bull agent and a bear agent can analyze the same metric to argue their market theses. Instead of relying on gut feelings, your agents use hard on-chain indicators to reach consensus. This grounding prevents your multi-agent system from drifting into speculative loops.

Run point-in-time simulations across agents

The `get_pit_metric` tool gives your debate agents historical snapshots to simulate past market crises. A risk officer agent uses this data to challenge the execution strategies of a trading agent. They negotiate based on the actual on-chain conditions of past market tops or bottoms. This pressure-tests your strategies in realistic environments before risking capital.

Scan thousands of assets via this MCP Server

The `get_bulk_metric` tool pulls data for all supported assets in one go using the `a="*"` parameter. An allocator agent parses this bulk payload to distribute capital across the strongest networks. Meanwhile, a compliance agent monitors the same stream to flag assets with low liquidity. The agents collaborate in real time to rebalance your portfolio based on live network activity.

Setup guide

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

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Glassnode (On-chain Data) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Glassnode (On-chain Data)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Glassnode (On-chain Data) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Glassnode (On-chain Data)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Glassnode (On-chain Data) data")
    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 AutoGen

Import `mcp_server_tools` from `autogen-ext[mcp]` and configure the MCP server URL. Pass the resulting tool list directly to your `AssistantAgent` constructor to give them on-chain capabilities.

Yes, one agent can call `get_metric_details` to verify the exact definition and parameters of a metric. It can then present these details to the group to resolve any analytical disputes.

One agent runs `list_assets` to get the master list. It then delegates specific asset chunks to other agents, who query `get_metric` in parallel to keep the analysis fast.

The `McpToolAdapter` automatically translates the raw JSON outputs into structured formats that AutoGen agents can easily parse, discuss, and act upon.

No, the MCP server handles credential injection at the transport layer on Vinkius. Your agents only see the resulting metric data, keeping your credentials hidden from the conversation logs.

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