Bring Customer Success
to OpenAI Agents SDK
Learn how to connect Custify 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 Custify MCP Server?
Connect your Custify customer success account to any AI agent and simplify how you manage your product users, track account health, and monitor churn risk through natural conversation.
What you can do
- User & Company Oversight — List all managed people and organizations and retrieve detailed metadata and health scores.
- Health Monitoring — Query health score metrics and values to identify at-risk customers and churn signals instantly.
- Event Tracking — Record custom user actions and events programmatically to feed your success analytics.
- Segment Analysis — List and query defined customer segments to understand your user distribution.
- CRM Control — Create new person records and update profile data directly via AI commands.
- Engagement Insights — Fetch engagement history and metadata for individual accounts directly from the agent.
How it works
1. Subscribe to this server
2. Enter your Custify API Key (found in your account settings)
3. Start managing your customer success lifecycle from Claude, Cursor, or any MCP client
Who is this for?
- Customer Success Managers (CSMs) — quickly check account health and track recent user events via simple AI queries.
- Success Operations — monitor segment distributions and verify company metadata directly from the workspace.
- Product Teams — track custom feature adoption events and monitor user profile quality via the AI assistant.
Built-in capabilities (8)
Create a new person record
Get details for a specific company
Get details for a specific person
List customer companies
List customer health scores
List product users (people)
List user segments
Track a custom event
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 8 tools from Custify through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Custify, 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
Custify in OpenAI Agents SDK
Custify and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Custify 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 Custify in OpenAI Agents SDK
The Custify 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
Custify for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Custify 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 health score of a company via AI?
Yes! Use the get_company_details tool and provide the Company ID. Your agent will retrieve the current health score, risk status, and account metadata.
How do I track a custom user event using the agent?
Use the track_user_event action. Provide the User ID and the Event Name. You can also pass a JSON object with additional attributes for the action.
Is it possible to see my defined customer segments via AI?
Absolutely. Use the list_user_segments query. The agent will retrieve the complete list of segments configured in your Custify account.
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.
