Bring Customerly
to OpenAI Agents SDK
Learn how to connect Customerly 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 Customerly MCP Server?
Connect your Customerly account to any AI agent and take full control of your customer success and support workflows through natural conversation.
What you can do
- User & Lead Orchestration — Create and manage customer profiles programmatically, including synchronizing custom attributes and managing lifecycle status
- Conversation Intelligence — Access complete chat histories and retrieve detailed interaction metadata to provide high-fidelity context for support
- Engagement Tracking — Monitor active chat sessions and customer interactions in real-time to optimize your team's response strategy
- Audience Segmentation — Programmatically add or remove tags for users and leads to maintain a structured and personalized communication ecosystem
- Record Management — Securely delete user records or update contact identification to ensure your database remains perfectly coordinated and compliant
How it works
1. Subscribe to this server
2. Retrieve your API Access Token from the Customerly dashboard (Settings > API)
3. Start managing your customer relationships from Claude, Cursor, or any MCP client
No more manual ticket searching or digging through user tables in the portal. Your AI acts as your dedicated success engineer and support coordinator.
Who is this for?
- Customer Success Teams — instantly retrieve user profiles and summary interaction histories using natural language commands
- Marketing Automation Leads — automate the tagging and segmentation of new leads without leaving your workspace
- Product Managers — track user engagement and sync backend metadata through simple AI queries
Built-in capabilities (8)
Provide tag name and contact identification. Add a tag to a contact
Create or update a lead
Provide email and optionally user_id, name, and attributes. Create or update a user
Delete a user
Get details of a specific conversation
List all conversations
List all users
Remove a tag from a contact
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 8 tools from Customerly through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Customerly, 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
Customerly in OpenAI Agents SDK
Customerly and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Customerly 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 Customerly in OpenAI Agents SDK
The Customerly 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
Customerly for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Customerly 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 find my Customerly Access Token?
Log in to your Customerly dashboard, navigate to Settings > API, and generate or copy your Access Token.
Can I read full chat histories?
Yes! The get_conversation tool retrieves the detailed message log and interaction metadata for any specific conversation ID.
How do I add tags to a user?
Use the add_tag tool and provide the tag name along with either the user's email or their unique user_id.
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.