How to Use the Intercom MCP in Pydantic AI

Q: Can I use this setup to search and filter contacts safely?

Yes, your agent can call searchcontacts with specific filter parameters. The results are parsed into type-safe models, preventing runtime errors when handling complex nested contact data.

Q: How is my workspace metadata protected by this integration?

All queries to read sensitive attributes via listdataattributes run inside a zero-trust, ephemeral V8 sandbox hosting the MCP Server on Vinkius. No data is stored, and your API credentials are encrypted end-to-end.

Build zero-hallucination support workflows using Pydantic AI to validate every single Intercom API response at runtime.

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 contact management with Pydantic AI

The `create_contact` tool registers new users, but Pydantic AI ensures the payload matches your strict schema before hitting the API. If a field contains invalid data, the framework halts execution instantly. This strict validation prevents malformed data from corrupting your database when calling the MCP Server. The agent uses `get_contact_details` to verify existing profiles, parsing the response into strongly-typed Python objects.

Strict conversation validation

The `reply_to_conversation` tool lets your agent write back to customers safely. Pydantic AI validates the structure of the reply object, checking that required fields like conversation ID are present and correctly formatted. To construct these replies, the agent calls `list_help_articles` to find accurate reference material. The retrieved articles are validated against your schema before the model reads them, stopping bad formatting in its tracks.

Structural workspace auditing

The `list_data_attributes` tool retrieves all custom fields configured in your workspace via the MCP endpoint. Your agent parses this metadata to identify deprecated or non-standard attributes that need cleanup. By calling `list_segments`, the agent maps out user distributions across your platform. Because every record is validated at runtime, you can run automated audits without worrying about unexpected null values breaking your pipeline.

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-alternative-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

Use the unified MCPToolset constructor passing your external Vinkius server HTTP URL. Register the toolset by passing it to the toolsets parameter of your Agent instance.

The framework will fail loudly with a validation error rather than passing corrupt data to your model. This guarantees that tools like get_conversation_details always return structured, expected types.

Pass your Vinkius HTTP endpoint directly into the MCPToolset. The MCP Server fully supports both Streamable HTTP and SSE transports for reliable, type-safe communication.

Yes, your agent can call search_contacts with specific filter parameters. The results are parsed into type-safe models, preventing runtime errors when handling complex nested contact data.

All queries to read sensitive attributes via list_data_attributes run inside a zero-trust, ephemeral V8 sandbox hosting the MCP Server on Vinkius. No data is stored, and your API credentials are encrypted end-to-end.

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