Intercom MCP Server for OpenAI Agents SDKGive OpenAI Agents SDK instant access to 12 tools to Create Contact, Create Conversation, Get Contact Details, and more
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Intercom through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
Ask AI about this App Connector for OpenAI Agents SDK
The Intercom app connector for OpenAI Agents SDK is a standout in the Talk To Me category — giving your AI agent 12 tools to work with, ready to go from day one.
Vinkius delivers Streamable HTTP and SSE to any MCP client
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="Intercom Assistant",
instructions=(
"You help users interact with Intercom. "
"You have access to 12 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Intercom"
)
print(result.final_output)
asyncio.run(main())
* 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 Intercom MCP Server
Connect your Intercom account to any AI agent and manage customer communications through natural conversation.
The OpenAI Agents SDK auto-discovers all 12 tools from Intercom through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Intercom, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Contact Management — List contacts, inspect profiles with tags and custom attributes, and search by email or name
- Conversation Tracking — Browse all conversations, inspect threads with full message history, and monitor status
- Messaging — Send messages to contacts and reply to active conversations
- Company Records — List companies, inspect profiles with user counts and custom data
- CRM Search — Search contacts and companies using Intercom's query syntax
- Admin Management — List all team members and their roles
The Intercom MCP Server exposes 12 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.
All 12 Intercom tools available for OpenAI Agents SDK
When OpenAI Agents SDK connects to Intercom through Vinkius, your AI agent gets direct access to every tool listed below — spanning conversational-ai, helpdesk, customer-messaging, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.
Register a new contact
Start a new conversation
Get details for a contact
Get conversation history
List workspace admins
List Intercom contacts
List recent conversations
List custom attributes
List help center articles
List workspace segments
Reply to a conversation
Search contacts with filters
Connect Intercom to OpenAI Agents SDK via MCP
Follow these steps to wire Intercom into OpenAI Agents SDK. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.
Install the SDK
pip install openai-agents in your Python environmentReplace the token
[YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.comRun the script
python agent.pyExplore tools
Why Use OpenAI Agents SDK with the Intercom MCP Server
OpenAI Agents SDK provides unique advantages when paired with Intercom 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
Intercom + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Intercom MCP Server delivers measurable value.
Automated workflows: build agents that query Intercom, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries Intercom, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Intercom tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Intercom to resolve tickets, look up records, and update statuses without human intervention
Example Prompts for Intercom in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Intercom immediately.
"Show all open conversations and the contact details for the most recent one."
"Search for all contacts at acmecorp.com and list their companies."
"Send a follow-up message to Ana Costa and list all team admins."
Troubleshooting Intercom MCP Server with OpenAI Agents SDK
Common issues when connecting Intercom to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Intercom + OpenAI Agents SDK FAQ
Common questions about integrating Intercom MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
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?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.