Bring Digital Assets
to Pydantic AI
Learn how to connect Fireblocks to Pydantic AI and start using 40 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Fireblocks MCP Server?
Connect your Fireblocks workspace to any AI agent to orchestrate institutional-grade digital asset operations through natural language conversation.
What you can do
- Vault Management — List, create, and inspect vault accounts and asset balances across your entire organization.
- Transaction Orchestration — Create, estimate fees, and monitor transactions across multiple blockchains with full lifecycle control.
- Wallet Connectivity — Manage internal and external wallets, and generate new deposit addresses for various assets.
- Advanced Asset Support — Interact with NFTs, staking positions, and smart contracts directly from the console.
- Compliance & Security — Validate travel rules, manage gas station settings, and retrieve screening information for transactions.
How it works
- Subscribe to this server
- Enter your Fireblocks API Key and Private Key
- Start managing your digital asset infrastructure from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Treasury Managers — instantly check balances across hundreds of vaults and initiate transfers without manual dashboard navigation.
- DevOps Engineers — automate the creation of vault accounts and deposit addresses during deployment workflows.
- Compliance Officers — quickly retrieve screening results and validate travel rule data for specific transactions.
Built-in capabilities (40)
Add an asset/address to a wallet
Add a new contract to the whitelist
Cancel a pending transaction
Create a new external wallet container
Create a new internal wallet container
Create a new transaction (Transfer, Mint, Burn, etc.)
Create a new vault account
Create a new wallet for an asset in a vault
Generate a new deposit address
Create a new webhook subscription
Drop an ETH/EVM transaction
Estimate fees for a potential transaction
Get current network fee estimates for an asset
Get details for a contract asset
Retrieve gas station settings
Get the public key for a specific derivation path
Get compliance screening results for a transaction
Get details of a specific transaction
Retrieve details for a specific vault account
Get balance for a specific asset in a vault
List all supported assets
List all supported blockchains
List whitelisted contracts
List all external wallets
List all internal wallets
List all owned NFT tokens
List supported staking chains
List active staking positions
Retrieve transaction history with filters
List Virtual Asset Service Providers (VASPs)
List deposit addresses for an asset
List vault accounts with pagination
List notifications sent to a webhook
Refresh NFT data for a vault account
Register a custom asset (e.g., ERC-20)
Resend failed webhooks
Initiate a staking position
Update auto-fueling thresholds
Rename a vault account
Validate a transaction against Travel Rule requirements
Why Pydantic AI?
Pydantic AI validates every Fireblocks tool response against typed schemas, catching data inconsistencies at build time. Connect 40 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Fireblocks integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Fireblocks connection logic from agent behavior for testable, maintainable code
Fireblocks in Pydantic AI
Fireblocks and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Fireblocks to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Fireblocks in Pydantic AI
The Fireblocks MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 40 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Fireblocks for Pydantic AI
Every tool call from Pydantic AI to the Fireblocks MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I check the balance of a specific asset in a vault account?
Yes. Use the get_vault_account_asset tool by providing the Vault Account ID and the Asset ID. The agent will return the available, total, and pending balances.
How do I estimate transaction fees before sending funds?
You can use the estimate_fee tool. Provide the transaction details, and the agent will return the estimated network fees for different priority levels.
Is it possible to list all supported blockchains in my workspace?
Yes, the list_blockchains tool retrieves a comprehensive list of all blockchain networks currently supported and configured in your Fireblocks environment.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Fireblocks MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
TVMaze
15 toolsSearch TV shows, get episode guides, browse schedules, discover cast and crew — no API key required.
Bilibili Live
10 toolsAutomate VTuber interaction parsing via Bilibili Live — monitor super-chats, extract danmaku streams, and manage host rooms natively from any AI agent.
vote.direct
5 toolsManage voter info — audit polling locations, elections, and registration via IA.
Toket
8 toolsAccept crypto payments on your website with a checkout widget that supports Bitcoin, Ethereum, and major stablecoins.