How to Use the Fireblocks MCP in LangChain

Q: How does LangChain handle a failed transaction execution via Fireblocks?

If a Fireblocks tool like createtransaction returns an API error, the LangChain agent catches the exception. You can configure the agent to retry the operation or call droptransaction to clear the queue.

Q: Can I use the Fireblocks server to manage custom ERC-20 tokens within LangChain?

Absolutely. Your LangChain agent can call registerasset to add custom tokens, making them immediately available for Fireblocks vault operations and balance checks across all your chains.

Run complex multi-step digital asset workflows directly inside your LangChain pipelines using 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 LangChain

Create your Vinkius account to connect Fireblocks 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 Fireblocks with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step transactional chains

Let your LangChain agent run complex, multi-step financial flows without writing custom glue code using `create_vault_account`. Because LangChain handles sequential execution, the output of your Fireblocks vault setup feeds directly into the next transaction.

Observability for Fireblocks MCP Server operations

Track every single Fireblocks transaction request and fee check using LangSmith tracing when executing `estimate_network_fee`. This LangSmith visibility keeps your automated Fireblocks treasury operations accountable.

Automated compliance and transfer workflows

Build defensive LangChain chains that verify regulatory requirements via `list_vasps` before moving any Fireblocks assets. If the Fireblocks compliance check flags an issue, the LangChain pipeline halts and routes the details to your security channel.

Setup guide

Set up Fireblocks 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 Fireblocks 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({
    "fireblocks-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 Fireblocks 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 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 LangChain

LangChain chains these Fireblocks tools natively using runnables. For example, the agent can take the vault ID from `create_vault_account` and immediately feed it into `create_vault_account_asset` to initialize a wallet in a single execution loop.

Yes. By using LangSmith with this Fireblocks MCP server, every tool call like `get_transaction` or `estimate_fee` is logged with precise millisecond latency and token usage metrics.

If a Fireblocks tool like `create_transaction` returns an API error, the LangChain agent catches the exception. You can configure the agent to retry the operation or call `drop_transaction` to clear the queue.

Absolutely. Your LangChain agent can call `register_asset` to add custom tokens, making them immediately available for Fireblocks vault operations and balance checks across all your chains.

The Fireblocks MCP server only exposes transaction metadata, vault balances, and public key info via `get_public_key_info` to your LangChain agent. Your private keys remain secured inside the Fireblocks hardware security modules, meaning the agent never sees or touches actual signing keys.

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