How to Use the Blockscout MCP in AutoGen

Q: How do I register Blockscout MCP tools in AutoGen?

Install the extension with pip install -U "autogen-extmcp". Use StreamableHttpServerParams to point to your Vinkius endpoint, then pass the tools to your AssistantAgent.

Q: Can multiple AutoGen agents use the Blockscout tools simultaneously?

Yes, agents share the toolset. One agent can call getblock while another calls gettoken as part of their conversational workflow.

Q: How does this Blockscout MCP Server handle JSON-RPC calls in AutoGen?

Agents can execute raw Ethereum calls using the jsonrpc tool. The framework handles the JSON schema conversions automatically so agents can focus on analyzing the output.

Build multi-agent AutoGen teams that debate, analyze, and verify Blockscout blockchain transactions through collaborative consensus using our managed 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 Blockscout MCP to AutoGen

Create your Vinkius account to connect Blockscout 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 Blockscout with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent blockchain debate via AutoGen

Set up a security agent and an audit agent to analyze smart contracts. One agent pulls source code with `get_contract_source_code`, while the other cross-references it with `get_logs`. By using this MCP Server, your agents debate potential vulnerabilities. They reach consensus on contract safety before suggesting any actions to the user.

Coordinate complex wallet audits

Let one agent track native funds using `get_account_balance` while another inspects token holdings via `list_token_balances`. They compare notes to build a complete profile. If discrepancies show up, a third agent can query `get_account_internal_transactions` to find hidden contract calls. They collaborate in real time to map the entire flow.

Multi-agent transaction validation

When a transaction occurs, your AutoGen agents use `get_transaction` and `get_indexing_status` to verify its completion. One agent checks the block confirmation while another monitors indexing. This collaborative approach ensures no single agent misinterprets raw EVM data. They verify the transaction state together, reducing false positives.

Setup guide

Set up Blockscout 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 Blockscout 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="Blockscout_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the extension with `pip install -U "autogen-ext[mcp]"`. Use `StreamableHttpServerParams` to point to your Vinkius endpoint, then pass the tools to your `AssistantAgent`.

Yes, agents share the toolset. One agent can call `get_block` while another calls `get_token` as part of their conversational workflow.

Agents can execute raw Ethereum calls using the `json_rpc` tool. The framework handles the JSON schema conversions automatically so agents can focus on analyzing the output.

Yes, the adapter supports streamable HTTP transports. This allows your agents to receive real-time updates when querying tools like `get_logs`.

The server only queries public ledger data, including transaction hashes, block numbers, and ABI strings. All connections run through Vinkius's secure, zero-trust ephemeral sandbox.

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