How do I get a Custify API Key?

Log in to your Custify account, navigate to **Settings > API**, and you will find your API Key there. Ensure you have the necessary permissions to manage customer data.

Can the agent update health scores?

This integration currently focuses on listing and retrieving data. Health scores are typically calculated automatically by Custify based on usage and interaction data.

Does Custify support B2B company tracking?

Yes, Custify allows you to track both individual customers and company-level entities, which is fully supported by this integration.

Custify MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Custify
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Custify through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Custify Assistant",
            instructions=(
                "You help users interact with Custify. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Custify"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About Custify MCP Server

Integrate Custify, the comprehensive customer success platform, directly into your AI workflow. Monitor customer health, track churn risks, and manage your success tasks and notes using natural language.

The OpenAI Agents SDK auto-discovers all 10 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.

What you can do

Customer Oversight — List and retrieve detailed profiles, health scores, and churn probabilities for all customers.
Company Monitoring — Access company-level metrics and success data to manage B2B relationships effectively.
Success Task Management — List and track open tasks and internal CRM notes for your accounts.
KPI Discovery — Explore key performance indicators and metrics defined in your Custify account.

The Custify MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Custify to OpenAI Agents SDK via MCP

Follow these steps to integrate the Custify MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Custify

Why Use OpenAI Agents SDK with the Custify MCP Server

OpenAI Agents SDK provides unique advantages when paired with Custify through the Model Context Protocol.

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 + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Custify MCP Server delivers measurable value.

Automated workflows: build agents that query Custify, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Custify, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Custify tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Custify to resolve tickets, look up records, and update statuses without human intervention

Custify MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Custify to OpenAI Agents SDK via MCP:

create_customer_profile

Resolves the newly generated customer ID and validation status. Mutates the customer database state. Create a new customer profile in Custify

get_company_details

Resolves organizational attributes and health metrics. Touches the core company repository. Get detailed settings and metrics for a specific company

get_customer_details

Resolves health scores, recent activity, and segment membership. Interacts with the behavioral analytics boundary. Get full profile and health metrics for a specific customer

list_companies

Resolves company IDs, domain information, and association metrics. Touches the account-level organization boundary. List all companies in Custify

list_customer_kpis

Resolves metric definitions and threshold values. Interacts with the performance monitoring boundary. List key performance indicators defined in the account

list_customer_notes

Resolves note content and authorship metadata. Touches the internal communications boundary. List internal CRM notes for a specific customer

list_customer_success_tasks

Resolves task priority, status, and assigned owners. Interacts with the workflow automation boundary. List open and completed customer success tasks

list_customers

Resolves properties such as customer ID, name, email, and lifecycle stage. Interacts with the customer success management boundary. List all customers in Custify

list_people

Resolves contact details and account associations. Touches the relationship management boundary. List all people associated with accounts

search_customers_by_keyword

Resolves matching customer profiles based on name or email. Touches the search and indexing boundary. Search for customers by name or email

Example Prompts for Custify in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Custify immediately.

"List all customers with a health score below 50."

"Show me the success tasks for company 'Alpha Corp'."

"Search for customer 'john.doe@example.com'."

Troubleshooting Custify MCP Server with OpenAI Agents SDK

Common issues when connecting Custify to OpenAI Agents SDK through the Vinkius, and how to resolve them.

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.

Custify + OpenAI Agents SDK FAQ

Common questions about integrating Custify MCP Server with OpenAI Agents SDK.

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.