Compatible with every major AI agent and IDE
What is the Superblocks MCP Server?
Connect your Superblocks organization to any AI agent to streamline the management of your internal applications and automated workflows. This server allows you to orchestrate your low-code ecosystem through natural language.
What you can do
- Application Management — List all organizational applications, fetch detailed configurations, and create or update apps programmatically.
- Workflow Orchestration — Retrieve a comprehensive list of all active workflows to monitor your backend logic and scheduled jobs.
- Secure Embedding — Generate authenticated session tokens for Embedded Apps, enabling seamless SSO integration for your end-users.
- Lifecycle Control — Perform maintenance by updating application payloads or deleting obsolete resources directly from your chat interface.
How it works
- Subscribe to this server
- Enter your Superblocks API Key
- Start managing your internal tooling infrastructure from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Internal Tools Engineers — quickly audit application configurations and manage resource lifecycles without leaving the terminal or IDE.
- DevOps Teams — monitor active workflows and automate the deployment or update of Superblocks applications.
- Product Managers — list available internal tools and generate embed tokens for stakeholder reviews or client integrations.
Built-in capabilities (7)
Create a new Superblocks application
Used to request session tokens for users when embedding Superblocks applications via SSO. Create an authenticated session token for Embedded Apps
Delete a Superblocks application
Retrieve details for a specific application
Supports pagination. List all applications in the organization
List all workflows in the organization
Update an existing Superblocks application
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 7 tools from Superblocks through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Superblocks, 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
Superblocks in OpenAI Agents SDK
Superblocks and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Superblocks 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 Superblocks in OpenAI Agents SDK
The Superblocks 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 7 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
Superblocks for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Superblocks MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I see all the internal tools currently built in my organization?
You can use the list_applications tool. It retrieves a paginated list of all Superblocks applications, allowing your AI to browse through your entire internal tool library.
Is it possible to generate a login token for a user to view an embedded app?
Yes, the create_embed_token tool is designed specifically for this. Provide the user's email and optional metadata to receive a secure session token for Embedded Apps.
Can I check the status of my backend workflows and scheduled jobs?
Absolutely. Use the list_workflows tool to get a full inventory of all workflows in your organization, which helps in monitoring your automated processes.
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 →
NOAA Aviation — Airport Weather Intelligence
5 toolsAviation weather data worldwide: METARs (current airport conditions), TAFs (24-hour airport forecasts), PIREPs (pilot reports of turbulence and icing), and SIGMETs/AIRMETs (significant aviation hazards) from the Aviation Weather Center.

OpenWeather Agro
12 toolsAccess agricultural weather and satellite data via OpenWeather — monitor NDVI, soil temperature, evapotranspiration, frost risk, and GDD from any AI agent.

SEC EDGAR Financials — Revenue, Income, Assets, EPS & Industry Comparison
4 toolsExtract XBRL financial data from SEC filings: revenue, net income, total assets, liabilities, stockholders' equity, EPS, and cash for any U.S. public company. Compare financial metrics across all companies industry-wide using XBRL frames. Like a free mini-Bloomberg terminal.

TomTom Parking Availability
3 toolsSearch parking spots — audit locations and availability via AI.
