How to Use the Arweave MCP in OpenAI Agents SDK

Q: How do I configure the Arweave MCP Server auto-discovery with the OpenAI Agents SDK?

Instantiate MCPServerStreamableHttp with your Vinkius endpoint and pass it to your Agent constructor. The OpenAI Agents SDK automatically registers tools like querygraphql and gettransaction on startup.

Q: How does the OpenAI Agents SDK handle Arweave transaction tracing?

All calls to tools like gettransactiondata are recorded in your OpenAI developer dashboard. You see the exact payload fetched from the permaweb alongside the agent's prompt history.

Q: Can my agent query the permaweb using GraphQL?

Yes, the agent can use querygraphql to run complex queries. This lets your python agent find specific transactions by tags without downloading the entire block history.

Deploy production-grade Python agents using the OpenAI Agents SDK to read, write, and audit permanent data directly on the Arweave permaweb.

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 OpenAI Agents SDK

Create your Vinkius account to connect Arweave to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Read permanent data inside OpenAI Agents SDK pipelines

The Arweave MCP Server lets your OpenAI Python agents inspect blockchain records directly during execution. Your agent can call `get_transaction_data` to pull raw data payloads or check confirmation states using `get_transaction_status` to ensure data has settled. These calls run natively inside your async Python workflows. The OpenAI dashboard traces every single transaction payload retrieved, matching gateway data to specific agent runs without extra logging code.

Write to the permaweb using OpenAI Agents SDK guardrails

This MCP Server enables secure data publishing by exposing the `submit_transaction` tool to your agent framework. Before sending data, your python agent can call `get_storage_price` to calculate exact Winston costs, letting your system-level guardrails approve or block the transaction based on your budget limits. By setting up multi-agent handoffs, you can have a specialized budget agent verify the cost via `get_wallet_balance` before handing the task back to the writing agent. This prevents runaway token spend during autonomous execution loops.

Audit blockchain health and network topology

The Arweave MCP Server exposes deep network diagnostics directly to your agentic system. Your agents can query `get_network_info` and `get_peers` to verify node distribution and gateway health before initiating heavy data queries. If a gateway behaves poorly, the agent dynamically adjusts its target node. You don't have to write custom retry logic because the agent handles the network fallback based on the peer lists it gets.

Setup guide

Set up Arweave MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Arweave tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Arweave tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Arweave tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Arweave Agent",
            instructions="You have access to Arweave tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Instantiate `MCPServerStreamableHttp` with your Vinkius endpoint and pass it to your Agent constructor. The OpenAI Agents SDK automatically registers tools like `query_graphql` and `get_transaction` on startup.

Yes, you can write validation checks that intercept agent actions. Before the agent calls `submit_transaction`, your guardrail can run `get_storage_price` to block any uploads exceeding your defined budget.

All calls to tools like `get_transaction_data` are recorded in your OpenAI developer dashboard. You see the exact payload fetched from the permaweb alongside the agent's prompt history.

Yes, the agent can use `query_graphql` to run complex queries. This lets your python agent find specific transactions by tags without downloading the entire block history.

Vinkius processes your requests in isolated V8 sandboxes, meaning your wallet addresses and query parameters are never stored. The network data fetched via `get_wallet_balance` passes through an ephemeral, zero-trust connection directly to your Python agent.

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