How to Use the BlockPi (Distributed RPC Network) MCP in AutoGen

Q: What transport protocol does AutoGen use to connect to BlockPi (Distributed RPC Network)?

It uses Streamable HTTP transport through the autogen-ext package to connect to this MCP Server. This allows your agents to communicate with the managed Vinkius host directly without needing a local node setup.

Q: Can an AutoGen agent execute raw EVM smart contract calls?

Yes, by passing the correct parameters to rpccall. The agent can formulate custom JSON-RPC payloads like ethcall to read contract variables directly from the supported blockchains.

Let AutoGen agents debate blockchain state and manage RPC budgets autonomously with 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 BlockPi (Distributed RPC Network) MCP to AutoGen

Create your Vinkius account to connect BlockPi (Distributed RPC Network) 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 BlockPi (Distributed RPC Network) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Budget Negotiations

Build a multi-agent system where one agent wants to query the chain and another guards the wallet. By using this MCP Server, your financial agent can call `get_wallet_balance` and `get_ru_balance` to audit the developer agent's requests. They can debate whether a specific `rpc_call` is worth the RU cost before executing it. This collaborative decision-making process prevents runaway loops from draining your funds.

Consensus-Driven Blockchain Actions in AutoGen

Ensure your Web3 agents agree on chain state before taking action. One AutoGen agent can fetch raw block data via `rpc_call`, while a separate validation agent checks the transaction details for potential anomalies. If the validation agent flags a risk, they discuss the issue in the conversation thread. No actions are taken until both agents reach consensus on the safety of the transaction data.

Automated Resource Allocation

Let your agents manage their own API packages in real time. An agent can call `get_package_expiration` to check if an active RU package is ending soon and coordinate with other agents to prioritize critical queries. By tracking `get_ru_consumed`, the agents can automatically redistribute workloads across different networks. They optimize their own operations without human intervention.

Setup guide

Set up BlockPi (Distributed RPC Network) 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 BlockPi (Distributed RPC Network) 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="BlockPi (Distributed RPC Network)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent BlockPi (Distributed RPC Network) 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="BlockPi (Distributed RPC Network)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent BlockPi (Distributed RPC Network) 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 BlockPi. 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 BlockPi (Distributed RPC Network) 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 BlockPi (Distributed RPC Network) MCP in AutoGen

Your agents share a conversation space where they can pass tool results. For instance, one agent calls `get_ru_balance` and shares the remaining units, allowing the coordinator agent to decide if they should proceed with more expensive BlockPi calls.

Yes. You register the tool list returned by the McpToolAdapter only to specific AssistantAgent instances. This keeps your financial tools isolated to your budget agent while your coder agent remains read-only.

It uses Streamable HTTP transport through the `autogen-ext` package to connect to this MCP Server. This allows your agents to communicate with the managed Vinkius host directly without needing a local node setup.

Yes, by passing the correct parameters to `rpc_call`. The agent can formulate custom JSON-RPC payloads like `eth_call` to read contract variables directly from the supported blockchains.

Vinkius manages your API credentials securely on the server side, so they are never exposed to the AutoGen conversation history. All JSON-RPC payloads pass through ephemeral V8 isolates that are destroyed immediately after execution.

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