How to Use the Intercom MCP in Pydantic AI

Q: How do I initialize the Intercom MCP Server in Pydantic AI?

Install the framework using pip install "pydantic-ai-slimmcp". Use the MCPToolset class to connect to your Vinkius HTTP endpoint, then pass that toolset directly to your agent's toolsets parameter.

Q: How does Pydantic AI handle unexpected data from Intercom?

It fails loudly. If a tool like getconversation returns fields that don't match your Pydantic models, the framework raises a validation error, preventing the agent from making incorrect decisions.

Q: Can my agent list all active team members?

Yes. The agent can call listadmins to fetch a validated list of your team members, which is useful for assigning tickets or checking who is currently on duty.

Build type-safe support agents using Pydantic AI and an MCP Server to interact with Intercom data with zero runtime schema errors.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Intercom MCP to Pydantic AI

Create your Vinkius account to connect Intercom to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Intercom with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe customer data management with Pydantic AI

Ensure data fetched via `get_contact` matches your exact schema to avoid silent failures in production. Pydantic AI enforces strict data validation on every response from this MCP Server. If the support API returns an unexpected payload structure, the framework raises a validation error immediately. This prevents your agent from acting on corrupt or hallucinated contact details. You get clean, predictable data every time.

Validate conversation threads before replying

Before invoking `reply_to_conversation`, the agent validates the entire thread history returned by `get_conversation` against strict Pydantic models. This workflow guarantees that your agent only replies to open, active threads. Parsing tags using `list_tags` ensures the conversation has not already been handled by a human agent. You avoid double-replying and embarrassing your brand.

Search and filter accounts with absolute certainty

Your agent uses `list_companies` and `search_contacts` to verify account status before offering high-priority support. Stop guessing if a customer belongs to an enterprise tier. Validating the company metadata at runtime happens automatically. This allows your agent to safely route tickets or pull help articles via `list_articles` knowing the underlying data is clean.

Setup guide

Set up Intercom MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "intercom-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Intercom tools.",
)

result = await agent.run("List recent Intercom transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Intercom. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Intercom now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Intercom MCP in Pydantic AI

Install the framework using `pip install "pydantic-ai-slim[mcp]"`. Use the `MCPToolset` class to connect to your Vinkius HTTP endpoint, then pass that toolset directly to your agent's `toolsets` parameter.

It fails loudly. If a tool like `get_conversation` returns fields that don't match your Pydantic models, the framework raises a validation error, preventing the agent from making incorrect decisions.

Yes, but you must run the server process externally. Pydantic AI connects to the running server via Streamable HTTP or SSE transports using the unified `MCPToolset` class.

Yes. The agent can call `list_admins` to fetch a validated list of your team members, which is useful for assigning tickets or checking who is currently on duty.

Your customer contacts, support messages, and conversation histories pass directly through secure, isolated V8 sandboxes. Vinkius handles the authorization token securely, meaning your raw credentials are never exposed to the LLM or stored on disk.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript