Bring Web3
to OpenAI Agents SDK
Learn how to connect QuickNode to OpenAI Agents SDK and start using 18 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 QuickNode MCP Server?
Connect your QuickNode account to any AI agent to orchestrate Web3 infrastructure through natural language. This server provides a comprehensive suite of tools to manage high-performance blockchain data pipelines and queries.
What you can do
- Streams Management — Create, list, and update real-time data streams for historical and live blockchain ingestion using
create_streamandlist_streams. - Webhooks — Deploy webhooks from templates (like EVM wallet filters or contract events) to deliver real-time events to your HTTP endpoints via
create_webhook. - KV Store — Manage key-value pairs and lists to power advanced server-side filtering logic for your streams using
create_kv_listandcreate_kv_set. - Core RPC — Access fundamental blockchain data, such as retrieving the most recent block number using
rpc_eth_blocknumber.
How it works
- Subscribe to this server
- Provide your QuickNode API Key and RPC URL
- Start building and monitoring your Web3 infrastructure from Claude, Cursor, or any MCP client
Who is this for?
- Web3 Developers — Rapidly prototype and manage data pipelines without leaving the terminal or IDE.
- Data Engineers — Orchestrate complex blockchain data ingestion workflows using natural language commands.
- DevOps Teams — Monitor and update infrastructure configurations, webhooks, and streams on the fly.
Built-in capabilities (18)
Create a new KV Store list
Create a KV Store key-value pair
Create a new QuickNode stream
Create a webhook from a template
Delete a KV Store key-value pair
Delete a QuickNode stream
Delete a QuickNode webhook
Retrieve items from a KV Store list
Retrieve a value from KV Store sets
Retrieve details of a specific QuickNode stream
List all active QuickNode streams
Retrieve all QuickNode webhooks
Returns the number of the most recent block
Executes a new message call immediately without creating a transaction
Returns an array of all logs matching a given filter object
Returns the receipt of a transaction by hash
Add or remove items from a KV Store list
Update an existing QuickNode stream
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 18 tools from QuickNode through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries QuickNode, 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
QuickNode in OpenAI Agents SDK
QuickNode and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect QuickNode 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 | 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 QuickNode in OpenAI Agents SDK
The QuickNode 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 18 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
QuickNode for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the QuickNode MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I check the current block height on Ethereum?
You can use the rpc_eth_blocknumber tool. It will return the most recent block number from the blockchain network connected to your RPC URL.
Can I create a stream to monitor specific blockchain datasets?
Yes, use the create_stream tool. You can specify the dataset (e.g., 'block', 'traces') and the destination (e.g., 'webhook', 's3') to start ingesting data immediately.
How do I manage lists for my stream filters?
Use the create_kv_list tool to initialize a list and update_kv_list to add or remove items. These lists can be referenced in your Streams JavaScript filter functions.
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.
Explore More MCP Servers
View all →
National Park Service
10 toolsAccess authoritative data about U.S. National Parks via NPS — track alerts, parks, and events directly from your AI agent.
FlightAware
12 toolsTrack global flight status via FlightAware AeroAPI — search flights, monitor airport arrivals and departures, check weather, and access historical flight data from any AI agent.
Smartsheet
6 toolsEmpower your AI to read Smartsheet rows, list workspaces, and manage your spreadsheets effortlessly from your code editor.
Discord Webhook Notifier
1 toolsThis MCP does exactly one thing: it sends messages to your Discord channels. That's its only function, and nothing else. Zero friction, incredible for giving your AI agents a voice.