Bring Conversational Ai
to Pydantic AI
Learn how to connect Intercom to Pydantic AI 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 Intercom MCP Server?
Connect your Intercom account to any AI agent and manage customer communications through natural conversation.
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
How it works
1. Subscribe to this server
2. Enter your Intercom Access Token from the developer hub
3. Start managing customers from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Support Teams — manage conversations and reply to customers through AI
- Sales Teams — search leads, inspect company profiles, and track engagement
- Customer Success — monitor conversations and contact activity
Built-in capabilities (12)
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
Why Pydantic AI?
Pydantic AI validates every Intercom tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through 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.
- —
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 in Pydantic AI
Intercom and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Intercom to Pydantic AI 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 Intercom in Pydantic AI
The Intercom 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 Pydantic AI 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
Intercom for Pydantic AI
Every tool call from Pydantic AI to the Intercom MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I search for contacts and send messages through the AI agent?
Yes. Use search_contacts to find contacts by email, name, or custom attributes. Then use send_message to send a message to a specific contact, or reply to an active conversation thread.
Can I view full conversation histories?
Yes. list_conversations shows all conversations with status. Use get_conversation with a conversation ID to retrieve the full message thread including sender, timestamps, and content.
What type of Intercom token do I need?
You need an Access Token from a Private App in the Intercom Developer Hub. This provides scoped API access with Bearer authentication against api.intercom.io.
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.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai