How to Use the Arweave MCP in LangChain

Q: How does LangChain handle Arweave transaction fees?

Your LangChain agent uses getstorageprice to fetch the current rate in Winstons. It then compares this price against the balance returned by getwalletbalance before attempting to call submittransaction in the next link of your chain.

Chain Arweave network queries and transaction checks directly into your LangChain agent workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arweave MCP to LangChain

Create your Vinkius account to connect Arweave 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 Arweave with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Calculate and verify storage costs in LangChain

The `get_storage_price` tool lets your agent fetch the exact cost in Winstons to store arbitrary data on the permaweb. Your LangChain agent can use this price data to decide if a file fits within your budget constraints before initiating any transfers. By feeding this output into the next chain link, the agent can check the wallet's current funds using `get_wallet_balance`. If the balance is sufficient, the chain proceeds; otherwise, it triggers a warning or halts the run, giving you full control over token spending.

Trace permaweb transactions with this MCP Server

This MCP Server exposes `get_transaction_status` and `get_transaction` so your agent can track data uploads over time. LangChain tracks these tool executions inside LangSmith, showing you the exact inputs, outputs, and latency of every blockchain query. When an agent needs to verify an upload, it runs `get_transaction_data` to confirm the content matches. If the transaction is still pending, the agent can loop back and check again later, making your automated workflows highly resilient to variable block times.

Query the block history programmatically

The `query_graphql` tool gives your LangChain agent a direct interface to search the entire Arweave network using flexible metadata tags. Instead of writing custom API integration code, you let the agent write and execute GraphQL queries based on natural language prompts. Once the agent finds the target transaction IDs, it can run `get_block_by_height` or `get_block_by_hash` to map those transactions back to specific blocks. This allows complex historical data analysis pipelines to run autonomously with zero manual coding.

Setup guide

Set up Arweave 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 Arweave 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({
    "arweave-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 Arweave 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 Arweave. 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 Arweave 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 Arweave MCP in LangChain

Your LangChain agent uses `get_storage_price` to fetch the current rate in Winstons. It then compares this price against the balance returned by `get_wallet_balance` before attempting to call `submit_transaction` in the next link of your chain.

Yes, every tool execution is fully logged. When your LangChain agent calls `get_transaction_data` or `get_network_info`, LangSmith records the latency, token count, and raw JSON payload, making debugging straightforward.

You configure the client using the multi-server adapter pointing to the Vinkius endpoint. This aggregates the Arweave toolset alongside your other databases or APIs, letting the agent call `get_peers` or `query_graphql` dynamically.

It uses standard SSE or stdio transports managed through the Vinkius gateway. You get a single secure endpoint that exposes all 13 tools to your agent without managing individual node connections.

Vinkius runs this toolset in an isolated V8 sandbox, meaning your queries to `get_wallet_last_tx` or `get_wallet_balance` are never stored. Only public blockchain data is fetched from the network, and your local agent configuration handles all private keys safely outside the server.

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