How do I get an API Token for Front?

Log in to your Front account, click the gear icon (Settings), go to 'Developers' > 'API Tokens', and create a new token with 'Shared Resources' scope.

Can I search for specific types of conversations?

Yes, use the 'search_conversations' tool. It accepts standard Front search syntax, such as 'is:open' or 'inbox:support'.

Is it possible to reply to an email via the agent?

Yes! Use the 'send_inbox_reply' tool. You must provide the Conversation ID, the message body, and the Teammate ID of the sender.

How do I archive a conversation?

Use the 'update_conversation_status' tool and set the status parameter to 'archived'. This updates the global status for the shared inbox.

Front MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Front
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Front through 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 Front "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Front?"
    )
    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 Front MCP Server

Connect your Front account to any AI agent to automate your customer communication and shared inbox workflows through the Model Context Protocol (MCP). Front is a customer operations platform that enables teams to manage shared emails, SMS, and chats collaboratively. This MCP server enables you to track active conversations, assign messages, and fetch thread histories directly through natural conversation.

Pydantic AI validates every Front 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.

Key Features

Shared Inbox Management — List all accessible shared inboxes and retrieve the specific conversations routed to them.
Conversation Tracking — Search and list all customer conversations, checking their current status (open, archived) and assigned owners.
Message Threading — Fetch the complete message history for any specific conversation to maintain context before replying.
Collaborative Replies — Draft and send replies to active conversations directly from your chat interface on behalf of a teammate.
Status Automation — Programmatically update conversation statuses (e.g., archiving resolved issues) to keep inboxes clean.
Team & Contact Discovery — List all workspace teammates and customer contacts to ensure accurate routing and messaging.

The Front MCP Server exposes 12 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 Front to Pydantic AI via MCP

Follow these steps to integrate the Front 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 12 tools from Front with type-safe schemas

Why Use Pydantic AI with the Front MCP Server

Pydantic AI provides unique advantages when paired with Front 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 Front integration code

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

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

Front + Pydantic AI Use Cases

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

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

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

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

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

Front MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Front to Pydantic AI via MCP:

get_conversation_details

Get conversation metadata

get_inbox_details

Get inbox metadata

list_address_book

List contacts

list_all_conversations

List all conversations

list_conversation_messages

List thread messages

list_inbox_teammates

List Front teammates

list_inbox_threads

List inbox conversations

list_shared_inboxes

List shared inboxes

search_conversations

g. "inbox:inb_123 is:open"). Search all conversations

send_inbox_reply

Send a reply

update_conversation_status

g., archived, open) or assignee of a conversation. Update conversation

verify_api_status

Verify connection

Example Prompts for Front in Pydantic AI

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

"List all shared inboxes in my Front account."

"Search for open conversations in the Support inbox."

"Archive conversation 'cnv_987'."

Troubleshooting Front MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Front + Pydantic AI FAQ

Common questions about integrating Front 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 Front MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.