How to Use the Covalent MCP in AutoGen

Q: How do I add the Covalent MCP Server to my AutoGen setup?

Run pip install -U "autogen-extmcp". Use mcpservertools with StreamableHttpServerParams to connect, then pass the resulting list into your AssistantAgent constructor.

Q: Does AutoGen handle Covalent schema conversions?

Yes. The McpToolAdapter automatically translates the JSON schemas for tools like getnftbalances into a format your conversational agents understand natively.

Give your AutoGen multi-agent squads access to live blockchain data and token metrics via this MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Covalent MCP to AutoGen

Create your Vinkius account to connect Covalent 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 Covalent with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve on-chain disputes via consensus

AutoGen shines when agents debate complex data. You can set up a security agent that reviews `get_transaction_details` to flag suspicious gas consumption metrics. A separate trading agent might argue that the transaction is standard for a high-volume DEX. They discuss the decoded event parameters and converge on a final risk assessment before alerting the user.

Delegate Covalent MCP Server queries

You don't need one massive agent trying to do everything. Assign `get_block_details` to a dedicated infrastructure agent that only monitors chain health and block timestamps. Meanwhile, a portfolio agent handles the financial side. It calls `get_historical_portfolio` to track asset valuations, passing its findings back to the group chat for the main assistant to summarize.

Automate deep wallet investigations

Tracing funds across networks takes serious deliberation. One agent can pull initial transfers using `get_token_transfers`, then ask a peer agent to investigate specific receiver addresses. The peer agent might then use `get_token_balances` on those new wallets to map out the current holdings. This back-and-forth negotiation uncovers connections a single-pass script would miss.

Setup guide

Set up Covalent 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 Covalent 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="Covalent_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Run `pip install -U "autogen-ext[mcp]"`. Use `mcp_server_tools` with `StreamableHttpServerParams` to connect, then pass the resulting list into your `AssistantAgent` constructor.

Yes. The `McpToolAdapter` automatically translates the JSON schemas for tools like `get_nft_balances` into a format your conversational agents understand natively.

You assign the tools to specific agents in the group. When a conversation requires chain data, the group routes the request to the agent holding the Covalent tools.

They figure it out through dialogue. If an agent isn't sure, it can call `list_supported_chains` to get human-readable names and chain IDs before attempting a specific wallet lookup.

We handle authentication at the platform level so you only need one endpoint token. Your block hashes and wallet queries execute inside a temporary container that gets destroyed right after the agent receives its answer.

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