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

Q: How does LangSmith help me debug BlockPi (Distributed RPC Network) calls inside LangChain?

LangSmith logs every single input and output for the rpccall tool in real time. You can inspect the exact JSON-RPC payload sent to the network and see the latency of the distributed nodes.

Run multi-step Web3 chains and track your node costs directly inside LangChain using 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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Blockchain Queries

Let your LangChain agents fetch live blockchain state and decide what to do next based on the payload. By wrapping `rpc_call` in this MCP server into your agentic chains, the model can grab an Ethereum block number, check a smart contract state, and feed that exact output into the next chain link. You don't need to hardcode the execution path. The agent evaluates the JSON-RPC response on the fly, switching tracks or querying different contracts based on the data it uncovers.

Real-Time Cost Control in LangChain Chains

Keep your chains from burning through cash by monitoring your RPC limits dynamically. Your agents can call `get_ru_balance` and `get_wallet_balance` before spinning up heavy data-gathering loops. If the remaining Request Units drop below your threshold, the LangChain agent pauses the run or switches to a cheaper fallback network. This keeps your automated pipelines from hitting a wall mid-execution.

Automated RU Optimization

This MCP Server lets your agents track exactly how much gas your queries are costing. Use `get_ru_consumed` to measure the cost of specific RPC endpoints during complex chain runs. By feeding these consumption metrics back into your LangSmith traces, you get a clear picture of which chain steps are draining your budget. Your agent can even swap to more efficient query patterns when it notices consumption spiking.

Setup guide

Set up BlockPi (Distributed RPC Network) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes BlockPi (Distributed RPC Network) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "blockpi-distributed-rpc-network-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent BlockPi (Distributed RPC Network) transactions"
    })
    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 LangChain

You use LangChain's routing mechanisms to pass the output of `rpc_call` straight into your next chain node. The raw JSON-RPC response flows natively as a string payload, meaning your next tool can parse and act on it immediately.

Yes. You can insert a step in your LangGraph or chain that checks `get_wallet_balance` first. If the USD balance is below a set limit, you programmatically halt the chain before executing any expensive blockchain calls.

LangSmith logs every single input and output for the `rpc_call` tool in real time. You can inspect the exact JSON-RPC payload sent to the network and see the latency of the distributed nodes.

No, this MCP server handles the routing internally. Your agent simply specifies the target network inside the `rpc_call` parameter, and the server routes it to the correct BlockPi node.

Your private keys never touch this server. Only public wallet addresses, RU balances, and read-only RPC payloads are processed, and Vinkius runs everything in an isolated, ephemeral sandbox that wipes all memory the moment your session ends.

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