How to Use the Meld MCP in AutoGen

Q: How do I register Meld tools with an AutoGen MCP client?

Use the autogen-extmcp package to connect to the MCP server's HTTP transport. Pass the adapted tools directly into your AssistantAgent constructor so they can be invoked during conversations.

Q: Can multiple AutoGen agents call Meld tools simultaneously?

Yes, agents can run tools like getaccountinfo or listwallets in parallel. The adapter handles schema conversion automatically, ensuring smooth multi-agent coordination.

Q: How do AutoGen agents handle errors from Meld tools?

If a tool call like getwalletdetails fails due to an invalid address, the calling agent receives the error. It can then request clarification from the user or another agent.

Deploy specialized AutoGen agents that debate portfolio strategies using real-time wallet and transaction data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Meld MCP to AutoGen

Create your Vinkius account to connect Meld 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 Meld with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate financial decisions.

This AutoGen configuration links your multi-agent conversations directly to the Meld multi-chain API for collaborative financial analysis. You set up a portfolio agent that calls `get_wallet_details` and a risk agent that analyzes `list_transactions` to debate asset allocation. This multi-agent setup ensures that financial decisions are thoroughly checked. One agent flags suspicious transaction patterns while another proposes rebalancing steps based on current holdings.

Negotiate exchange rates across multiple agents.

The Meld pricing and network verification tools allow your AutoGen agents to negotiate exchange rates during simulated trades. A trading agent pulls rates using `get_exchange_rates` while a compliance agent checks network fees via `get_network`. By debating the math before presenting a conclusion, the agents arrive at a consensus that minimizes slippage and avoids expensive network fees.

Coordinate multi-chain assets with this MCP Server.

The Meld multi-chain discovery tools let your AutoGen agents map out complex portfolios. Use this MCP Server to let your agents call `list_networks` and `list_assets` to find active tokens across different chains. Once discovered, the details are shared with the rest of the agent group. This allows your team of agents to build a shared map of a user's multi-chain assets without manual intervention.

Setup guide

Set up Meld 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 Meld 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="Meld_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the `autogen-ext[mcp]` package to connect to the MCP server's HTTP transport. Pass the adapted tools directly into your `AssistantAgent` constructor so they can be invoked during conversations.

Yes, agents can run tools like `get_account_info` or `list_wallets` in parallel. The adapter handles schema conversion automatically, ensuring smooth multi-agent coordination.

If a tool call like `get_wallet_details` fails due to an invalid address, the calling agent receives the error. It can then request clarification from the user or another agent.

The integration supports both stdio and streamable HTTP transports. For hosted deployments on Vinkius, the streamable HTTP transport provides the most reliable connection.

All communications are secured using single-token authentication over an encrypted channel. The Vinkius MCP sandbox ensures your transaction history and wallet details are processed ephemerally and never logged.

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