How to Use the Fireblocks MCP in AutoGen

Q: How do AutoGen agents coordinate to approve a Fireblocks MCP transaction?

One AutoGen agent creates the draft using Fireblocks createtransaction. A second auditor agent checks the transaction details with gettransaction and validates it against compliance rules before giving the final go-ahead.

Build multi-agent consensus workflows for secure asset management using AutoGen and the Fireblocks 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 Fireblocks MCP to AutoGen

Create your Vinkius account to connect Fireblocks 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 Fireblocks with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent consensus for high-value transfers

Set up a secure AutoGen multi-agent debate before executing any Fireblocks blockchain transaction with `create_transaction`. An AutoGen compliance agent runs `validate_travel_rule` and checks the whitelisted Fireblocks contracts via `list_contracts`.

Automated fee optimization using MCP Server tools

Let competing AutoGen agents negotiate the best time to execute Fireblocks transactions based on `estimate_network_fee` values. If Fireblocks gas fees are too high, the monitoring AutoGen agent debates the execution agent to delay the transfer.

Automated staking and liquidity management

Deploy specialized AutoGen agents to manage your yields using `list_staking_chains` to check available Fireblocks opportunities. Once they agree on the risk profile, the execution AutoGen agent calls `stake_position` to lock the Fireblocks assets.

Setup guide

Set up Fireblocks 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 Fireblocks 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="Fireblocks_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Fireblocks 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="Fireblocks_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Fireblocks 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 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 AutoGen

One AutoGen agent creates the draft using Fireblocks `create_transaction`. A second auditor agent checks the transaction details with `get_transaction` and validates it against compliance rules before giving the final go-ahead.

Yes. If a monitoring AutoGen agent detects a Fireblocks transaction is pending for too long, it instructs the execution agent to call `cancel_transaction` or `drop_transaction` to clear the queue.

You can restrict Fireblocks tool access at the AutoGen agent level. For example, give your compliance agent access to `validate_travel_rule` and your execution agent exclusive access to `create_transaction`.

Yes. Your AutoGen agents can set up webhook subscriptions using Fireblocks `create_webhook` and monitor incoming notifications with `list_webhook_notifications` to automate status updates.

No. Fireblocks webhook details and notifications processed by `list_webhook_notifications` are handled entirely within the secure MCP server environment, meaning AutoGen agents only debate parsed transaction states.

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