How to Use the Fireblocks MCP in OpenAI Agents SDK

Q: How does Fireblocks manage webhook notifications back to OpenAI Agents SDK?

You use createwebhook to register your endpoint. When status changes occur, Fireblocks sends a notification, and your OpenAI Agents SDK python server processes the event to trigger agent actions.

Q: What happens if a transaction stalls during an automated transfer?

Your agent calls gettransaction to monitor the status. If it remains pending, the agent executes droptransaction or canceltransaction to free up the vault account.

Deploy autonomous treasury agents that move assets and manage vaults safely using the Fireblocks MCP Server and OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fireblocks MCP to OpenAI Agents SDK

Create your Vinkius account to connect Fireblocks 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 Fireblocks with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Vault Provisioning

Setting up isolated deposit addresses starts with `create_vault_account` which your OpenAI Agents SDK agent executes dynamically during wallet onboarding. The agent then calls `create_vault_account_asset` to initialize specific tokens and runs `create_vault_account_asset_address` to hand a clean deposit address back to your user. Because OpenAI manages agent handoffs, you can run one agent for customer onboarding and another for treasury verification without leaking credentials. Your python code handles the routing while the agent updates the system status. If a customer needs a new blockchain, the agent runs `list_blockchains` to check support before attempting setup. You get full execution logs in the OpenAI dashboard to track exactly when and why a vault was provisioned.

Multi-Agent Compliance and Travel Rule Checks

Running transaction compliance requires calling `validate_travel_rule` before any digital assets leave your Fireblocks vault. Your specialized compliance agent built with OpenAI Agents SDK inspects the counterparty data, runs the check, and passes the approved payload to your transaction signer agent. This multi-agent handoff isolates sensitive client keys from the public-facing agent interface. When compliance fails, the agent stops the pipeline and logs the rejection. It queries `list_vasps` to check the destination provider's status and updates your internal database. You prevent unauthorized transfers at the SDK level before they ever hit the blockchain.

Secure Transaction Lifecycle in OpenAI Agents SDK

Initiating transfers requires `create_transaction` which your OpenAI Agents SDK agent calls using verified parameters from your database. The agent estimates the network cost beforehand by calling `estimate_network_fee` to prevent executing transfers during gas spikes. If a transaction stalls on-chain, the agent triggers `cancel_transaction` or `drop_transaction` to clear the queue. Built-in guardrails in the OpenAI Agents SDK validate these parameters against your custom safety schemas before sending them to the Fireblocks MCP Server. You track the entire lifecycle from execution to settlement by polling `get_transaction` within your async Python event loop.

Setup guide

Set up Fireblocks 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 Fireblocks tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Fireblocks 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="Fireblocks Agent",
            instructions="You have access to Fireblocks 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 Fireblocks. 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 Fireblocks 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 Fireblocks MCP in OpenAI Agents SDK

The server does not store your private keys directly. Your OpenAI Agents SDK agent uses `create_transaction` to initiate the transfer, which routes the request to your Fireblocks co-signer for secure signing.

Yes, you restrict tool access during initialization. You configure the OpenAI Agents SDK to only expose read-only tools like `get_vault_account` or `list_transactions` to public-facing agents, keeping write operations isolated.

You use `create_webhook` to register your endpoint. When status changes occur, Fireblocks sends a notification, and your OpenAI Agents SDK python server processes the event to trigger agent actions.

Your agent calls `get_transaction` to monitor the status. If it remains pending, the agent executes `drop_transaction` or `cancel_transaction` to free up the vault account.

This integration runs inside an ephemeral V8 sandbox, meaning your vault addresses, API keys, and transaction data are never stored on Vinkius servers. All requests go directly to the Fireblocks API, keeping your financial records completely isolated.

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