Bring Nft Minting
to OpenAI Agents SDK
Learn how to connect Toket to OpenAI Agents SDK and start using 8 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Toket MCP Server?
Connect your Toket account to any AI agent and simplify how you deploy NFT collections, mint digital assets, and monitor blockchain interactions through natural conversation.
What you can do
- Collection Management — List all your NFT collections and deploy new ERC-721 smart contracts instantly via AI.
- Asset Minting — Mint NFTs into specific collections or use 'Easy Mint' to quickly generate assets for recipients.
- Transaction Oversight — List and check the status of minting transactions to ensure successful blockchain delivery.
- Gas Management — Monitor your Gas Tank balance to keep your automated minting operations running smoothly.
- Metadata Control — Retrieve detailed metadata for collections and individual minted assets.
- Blockchain Visibility — Track the history of your digital asset distribution directly from the agent.
How it works
1. Subscribe to this server
2. Enter your Toket API Key (found in your account dashboard)
3. Start managing your Web3 ecosystem from Claude, Cursor, or any MCP client
Who is this for?
- Web3 Marketers — quickly mint rewards or loyalty NFTs for community members via simple AI commands.
- NFT Project Owners — monitor collection deployments and verify minting statuses across multiple chains.
- Developers — automate the creation of smart contracts and asset distribution directly from the workspace.
Built-in capabilities (8)
Provide name, symbol, and owner wallet. Create a new NFT collection
Quickly mint an NFT
Get details of a specific collection
Check Gas Tank balance
Get status of a minting transaction
List all NFT collections
List all minted NFTs
Mint an NFT into a collection
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 8 tools from Toket through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Toket, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Toket in OpenAI Agents SDK
Toket and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Toket to OpenAI Agents SDK 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 | 3,400+ 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 Toket in OpenAI Agents SDK
The Toket 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 8 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK 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
Toket for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Toket MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I deploy a new NFT collection using the AI?
Yes! Use the create_collection action. Provide a name, symbol, and the owner wallet address. Your agent will deploy a new ERC-721 smart contract instantly.
How do I check my remaining balance for transaction fees (Gas)?
Run the get_gas_tank_status query. The agent will retrieve your current Gas Tank balance to ensure you have enough funds for automated minting.
Is it possible to track the status of an NFT minting process?
Absolutely. Use the get_mint_status tool and provide the Transaction ID. Your agent will return the real-time status of the blockchain interaction.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
