How to Use the Messari MCP in AutoGen

Q: How do AutoGen agents share Messari tool outputs?

When an agent calls getassetdetails, the resulting JSON payload is automatically posted to the group chat. All other agents in the AutoGen session can read and analyze this data immediately.

Q: Can one AutoGen agent pull Messari metrics while another analyzes news?

Yes. You assign getassetmetrics to your analyst agent and getcryptonews to your researcher agent. They work in parallel and share their findings in the conversation thread.

Let AutoGen agents debate market trends and verify crypto data using Messari tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Messari MCP to AutoGen

Create your Vinkius account to connect Messari 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 Messari with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve Agent Debates with Messari Metrics

The `get_asset_metrics` tool provides the objective data foundation that AutoGen agents need to resolve conflicting strategies. When a trading agent and a risk agent disagree, they call this tool to analyze concrete on-chain numbers. By feeding verified data into the conversation, your agents stop guessing and start calculating. This MCP Server provides the ground truth that terminates endless debate loops.

Analyze Governance and News in Multi-Agent Workflows

The `list_governance_events` tool allows specialized compliance agents to monitor protocol proposals autonomously. The compliance agent retrieves active votes and presents them to the portfolio agent to adjust asset allocations. To evaluate market sentiment during these votes, the agents run `get_crypto_news` to gather external context. They discuss the news, weigh the risks, and reach a consensus before executing any simulated trades.

Verify Markets Across Multiple AutoGen Agents

The `list_crypto_markets` tool enables search agents to verify where a token is actively traded before suggesting a position. A separate execution agent can then cross-reference this with `list_crypto_exchanges` to confirm liquidity. This multi-agent verification loop ensures that no single agent acts on stale or unverified market listings. The MCP adapter automatically adapts the tool schemas, allowing seamless agent-to-agent data handoffs.

Setup guide

Set up Messari 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 Messari 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="Messari_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Messari 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="Messari_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Messari 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 Messari. 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 Messari 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 Messari MCP in AutoGen

When an agent calls `get_asset_details`, the resulting JSON payload is automatically posted to the group chat. All other agents in the AutoGen session can read and analyze this data immediately.

Yes. You assign `get_asset_metrics` to your analyst agent and `get_crypto_news` to your researcher agent. They work in parallel and share their findings in the conversation thread.

The MCP adapter handles the schema conversion automatically. It translates the server's tools, like `get_asset_profile`, into the format expected by the AutoGen assistant agent.

The error message is returned to the active agent as a chat message. The agent reads the error, corrects its parameters (such as resolving a token symbol via `search_assets`), and retries the call.

Your API token is stored as an environment variable on the host running the server. AutoGen agents only interact with the exposed tool interfaces and never have direct access to your raw credentials.

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