How do I get my Intercom Access Token?

Go to the **Intercom Developer Hub** at **app.intercom.com/a/developer-hub/**. Click **New app**, give it a name, and select the workspace to install it in. Once created, click on your app, then navigate to **Authentication** in the left sidebar. Your **Access Token** will be displayed on this page. Configure the required permissions (scopes) — such as Read/Write People, Conversations, or Companies — and click **Save**. Copy the token and paste it below.

Can I look up a customer's full conversation history instantly?

Yes. Just ask your AI agent 'Show me all conversations with john@acme.com' and it retrieves every conversation — open, closed, and snoozed — including message content, agent assignments, tags, and resolution times. Perfect for getting full context before a customer call.

Can I track support team performance metrics?

Yes. Your AI agent can pull conversation counts, average response times, resolution rates, and open ticket volumes — giving managers instant visibility into team workload and SLA compliance without building custom reports or opening the Intercom analytics dashboard.

Is my customer data secure?

Your Access Token is a private app token that only accesses data in your own Intercom workspace. It respects your workspace's permission model — the token only has access to the scopes you explicitly grant. All API calls are made over HTTPS, and the token is never shared with third parties.

Intercom MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Intercom
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Intercom through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

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 pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Intercom "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Intercom?"
    )
    print(result.data)

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 Intercom MCP Server

Connect Intercom to your AI agent and manage your customer communications and support operations conversationally.

Pydantic AI validates every Intercom tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Conversation Management — List, search, and manage customer conversations with status, assignment, and SLA data.
Contact Search — Query your customer database by email, name, company, or custom attributes to find specific users.
Company Data — Retrieve company profiles, plan information, and aggregate usage metrics.
Support Analytics — Pull conversation counts, response times, and resolution metrics for team performance reviews.

The Intercom MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI 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 Intercom to Pydantic AI via MCP

Follow these steps to integrate the Intercom MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Intercom with type-safe schemas

Why Use Pydantic AI with the Intercom MCP Server

Pydantic AI provides unique advantages when paired with Intercom through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Intercom integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Intercom connection logic from agent behavior for testable, maintainable code

Intercom + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Intercom MCP Server delivers measurable value.

Type-safe data pipelines: query Intercom with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Intercom tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Intercom and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Intercom responses and write comprehensive agent tests

Intercom MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Intercom to Pydantic AI via MCP:

get_contact

Get contact details

get_conversation

Get conversation thread

list_admins

List team members

list_articles

List help center articles

list_companies

List all companies

list_contacts

List all contacts/leads

list_conversations

List all conversations

list_tags

List all tags

reply_to_conversation

Reply to a conversation

search_contacts

Search contacts by criteria

Example Prompts for Intercom in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Intercom immediately.

"Find the contact record for sarah@startup.io."

"How many open conversations do we have right now?"

"List all companies on our Enterprise plan."

Troubleshooting Intercom MCP Server with Pydantic AI

Common issues when connecting Intercom to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Intercom + Pydantic AI FAQ

Common questions about integrating Intercom MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Intercom MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.