Compatible with every major AI agent and IDE
What is the Arbiscan (Arbitrum Explorer) MCP Server?
Connect your AI agent to Arbiscan to query the Arbitrum L2 network in real-time. This MCP server allows you to fetch blockchain data without leaving your chat interface or IDE.
What you can do
- Account Auditing — Check Ether balances for single or multiple addresses simultaneously.
- Transaction Tracking — Retrieve full history for normal, internal, ERC20, and ERC721 (NFT) transactions.
- Contract Intelligence — Fetch verified source code and ABIs to understand how dApps operate.
- Network Insights — Get real-time ETH price on Arbitrum, total supply, and block rewards.
- Developer Tools — Submit and verify contract source code directly through the API.
How it works
- Subscribe to this server
- Enter your Arbiscan API Key
- Start querying Arbitrum data from Claude, Cursor, or any MCP client
Who is this for?
- Web3 Developers — Inspect contract ABIs and source code while writing code in your IDE.
- Crypto Analysts — Track whale movements and token transfers using natural language.
- Security Researchers — Quickly audit transaction history and internal calls for suspicious activity.
Built-in capabilities (16)
Get Contract ABI for Verified Source Codes
Get Ether Balance for a Single Address
Get Ether Balance for Multiple Addresses
Get Estimated Block Countdown Time by BlockNo
Get Block Rewards by BlockNo
Get Ether Last Price
Get Total Supply of Ether on Arbitrum
Get Event Logs
Get Contract Source Code for Verified Source Codes
Check Contract Execution Status
Get List of ERC721 Token Transfer Events By Address
Get List of ERC20 Token Transfer Events By Address
Get List of Normal Transactions By Address
Get List of Internal Transactions By Address
Check Transaction Receipt Status
Verify Source Code
Why Pydantic AI?
Pydantic AI validates every Arbiscan (Arbitrum Explorer) tool response against typed schemas, catching data inconsistencies at build time. Connect 16 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 Arbiscan (Arbitrum Explorer) integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Arbiscan (Arbitrum Explorer) connection logic from agent behavior for testable, maintainable code
Arbiscan (Arbitrum Explorer) in Pydantic AI
Arbiscan (Arbitrum Explorer) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Arbiscan (Arbitrum Explorer) 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 Arbiscan (Arbitrum Explorer) in Pydantic AI
The Arbiscan (Arbitrum Explorer) 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 16 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
Arbiscan (Arbitrum Explorer) for Pydantic AI
Every tool call from Pydantic AI to the Arbiscan (Arbitrum Explorer) 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 balances of multiple Arbitrum addresses at once?
Yes! Use the get_balance_multi tool and provide a comma-separated list of addresses. The agent will return the Ether balance for each one in a single response.
How do I view the source code of a verified smart contract?
Simply provide the contract address to the get_source_code tool. If the contract is verified on Arbiscan, your agent will retrieve the full source code for you to inspect.
Can I track NFT (ERC721) transfers for a specific wallet?
Yes, the get_token_nft_tx tool allows you to list ERC721 token transfer events associated with any Arbitrum address, including block numbers and transaction hashes.
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 Arbiscan (Arbitrum Explorer) 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 →
Loop
10 toolsCollect customer feedback through micro-surveys that measure NPS, CSAT, and product sentiment without disrupting the user experience.

HowLongToBeat
1 toolsUniversal game completion data — get gameplay hours for any video game via AI.

OpenAI Alternative
13 toolsManage OpenAI resources via API — list models, monitor fine-tunes, manage batches and inspect Assistants from any AI agent.
Honeybadger (Error Tracking)
10 toolsMonitor app exceptions and uptime via Honeybadger — list projects, resolve faults, and track deployments.
