Bring Shared Inbox
to OpenAI Agents SDK
Learn how to connect Hiver to OpenAI Agents SDK and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Hiver MCP Server?
Connect your Hiver account to any AI agent and transform your Gmail-based customer support into an intelligent, automated operation through natural conversation.
What you can do
- Shared Inbox Management — List all shared mailboxes and retrieve detailed metadata for active email conversations
- Workflow Automation — Programmatically update conversation statuses (open, pending, closed) and manage assignments across your team
- Collaborative Drafting — Create shared drafts within Gmail threads directly through your agent to orchestrate perfect replies
- Tagging & Organization — Search and apply tags to categorize threads and maintain a high-fidelity collaboration ecosystem
- Team Visibility — List and search for inbox members to understand who is available and manage workload distribution
How it works
1. Subscribe to this server
2. Retrieve your API Key from the Hiver Admin Panel (Integrations > Developer APIs)
3. Start managing your shared support hub from Claude, Cursor, or any MCP client
No more context-switching between tools to check if a customer was replied to. Your AI acts as your dedicated inbox coordinator.
Who is this for?
- Support Teams — instantly triage inboxes, assign urgent threads, and check status without opening Gmail
- Operations Managers — monitor team workload and conversation volume through automated reports and queries
- Customer Success Leads — ensure high-priority threads are tagged and assigned to the right account managers in seconds
Built-in capabilities (12)
Draft team reply
Check connection
Read email thread
Get mailbox info
List shared threads
List team members
Get mailbox tags
List Hiver inboxes
Find tags
Find members
Verify credentials
Modify conversation
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 12 tools from Hiver through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Hiver, 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
Hiver in OpenAI Agents SDK
Hiver and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Hiver 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 Hiver in OpenAI Agents SDK
The Hiver 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 12 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
Hiver for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Hiver 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 an inbox ID?
Use the list_shared_inboxes tool to retrieve all shared mailboxes you have access to, along with their unique identifiers and names.
Can I assign a conversation to a specific teammate?
Yes! Use the update_thread_status tool and provide the assignee_id. You can find valid user IDs using the list_inbox_members tool.
Does Hiver support collaborative drafting through AI?
Yes, the create_shared_draft tool allows your AI agent to write directly into a Gmail thread, which your team can then review and send from the Hiver interface.
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.