Bring Product Management
to OpenAI Agents SDK
Learn how to connect Craft.io to OpenAI Agents SDK and start using 13 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Craft.io MCP Server?
Connect your Craft.io product management account to any AI agent and simplify how you coordinate your product strategy, manage features, and monitor roadmaps through natural conversation.
What you can do
- Workspace Oversight — List all product management workspaces and retrieve detailed metadata and configurations.
- Feature & Epic Tracking — List, query, and create new items (features, stories, epics) within your workspaces to manage your backlog.
- Portfolio Control — List and query product portfolios to understand high-level organizational distribution and strategy.
- Data Insights — Fetch complete metadata, descriptions, and current status for any specific product item via AI.
- Roadmap Monitoring — Track the progress of features and epics directly from your agent to stay on top of your release cycle.
- Operational Visibility — Check account status and verify project metadata directly from Claude, Cursor, or any MCP client.
How it works
1. Subscribe to this server
2. Enter your Craft.io API Key and Account ID (found in your account settings)
3. Start managing your product ecosystem from your favorite AI assistant
Who is this for?
- Product Managers & Owners — quickly retrieve feature details and update backlog items via simple AI commands.
- Engineering Leads — monitor epic progress and verify feature requirements directly from the workspace.
- Product Operations — manage workspace distributions and verify portfolio metadata via the AI assistant.
Built-in capabilities (13)
Verify connectivity
Create an item
Get company details
Get competitors
Get company employees
Get company financials
Get company news
Get item details
Get portfolio details
List workspace items
List portfolios
List workspaces
Search companies
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 13 tools from Craft.io through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Craft.io, 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
Craft.io in OpenAI Agents SDK
Craft.io and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Craft.io 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 Craft.io in OpenAI Agents SDK
The Craft.io 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 13 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
Craft.io for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Craft.io MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I see all the items in a specific workspace via AI?
Yes! Use the list_workspace_items tool and provide the Workspace ID. Your agent will retrieve all features, stories, and epics organized within that environment.
How do I add a new feature to my backlog using the agent?
Use the create_product_item action. Provide the Workspace ID and the title of the feature. The agent will instantly create the record in your Craft.io account.
Is it possible to list all my product portfolios via AI?
Absolutely. Use the list_product_portfolios query. The agent will retrieve the complete list of portfolios configured in your account, allowing you to monitor high-level strategy.
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.