What types of physical mail can I send with Lob?

Lob supports three main mail types: Letters (formal correspondence, invoices, notifications with customizable color, double-sided printing), Postcards (marketing campaigns, invitations, reminders in 4x6, 6x9, or 6x11 sizes), and Checks (vendor payments, payroll, refunds, rebates with customizable memo lines and company logos). All mail is printed and mailed within 24 hours via USPS.

How does Lob address verification work?

Lob's address verification validates and standardizes addresses using USPS data. It corrects formatting, adds missing ZIP+4 codes, fixes typos, and confirms deliverability. The service returns a deliverability status: 'deliverable' (valid and deliverable), 'undeliverable' (cannot be delivered), or 'deliverable_unnecessary' (valid but additional info not needed). This reduces returned mail by up to 5% and ensures your mailings reach the correct destination.

Can I use HTML templates for personalized mailings?

Yes! Lob supports HTML templates with merge variables using the Handlebars templating engine. Create a template with placeholders like {{name}}, {{order_number}}, {{delivery_date}}, then pass actual values when creating letters or postcards. This enables personalized, scalable direct mail campaigns. Templates are reusable and can be referenced by ID when creating mailings. You can also embed CSS styling for professional-looking mail designs.

How long does it take for mail to be delivered?

Lob prints and mails all items within 24 hours of creation. Delivery time depends on the mail type selected: USPS First Class Mail typically delivers in 2-5 business days, while USPS Standard Mail takes 3-7 business days. You receive a tracking number for each piece of mail to monitor delivery status. Lob also provides expected delivery dates in API responses for planning purposes.

Lob MCP Server for Pydantic AI 21 tools — connect in under 2 minutes

Name: Lob
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 21 Tools SDK

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

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

Lob MCP Server enables AI agents to send physical mail directly from your applications. Create and mail letters, postcards, and checks programmatically through Lob's print and mail API. Verify US and international addresses, autocomplete partial addresses, and manage your address book. Build reusable HTML templates for personalized mailings. Perfect for automating vendor payments, customer communications, marketing campaigns, payroll checks, and direct mail operations. All mail is printed, processed, and delivered within 24 hours via USPS integration.

Pydantic AI validates every Lob tool response against typed schemas, catching data inconsistencies at build time. Connect 21 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.

The Lob MCP Server exposes 21 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 Lob to Pydantic AI via MCP

Follow these steps to integrate the Lob 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 21 tools from Lob with type-safe schemas

Why Use Pydantic AI with the Lob MCP Server

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

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

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

Lob + Pydantic AI Use Cases

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

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

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

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

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

Lob MCP Tools for Pydantic AI (21)

These 21 tools become available when you connect Lob to Pydantic AI via MCP:

autocomplete_us_address

Autocomplete a partial US address

cancel_letter

Only works if status is still "processing". Cancel a letter before it enters production

create_address

Requires name and address_line1. Create a new address in your Lob address book

create_bank_account

Requires description, routing_number, account_number, account_type (company/individual), and signatory. Add a bank account for sending checks

create_check

Requires recipient (to), bank account ID, and amount. Optional: memo, logo, description. Create and mail a physical check through Lob

create_letter

Requires recipient (to), sender (from), and file content. Supports HTML templates with merge variables, color options, and mail type selection. Create and mail a physical letter through Lob

create_postcard

Requires recipient (to) and front design. Optional: back design, message, merge variables. Create and mail a physical postcard through Lob

create_template

Create a reusable HTML template for mailings

delete_address

Delete an address from your Lob address book

get_address

Get details of a specific address

get_check

Get details of a specific check by ID

get_letter

Get details of a specific letter by ID

get_postcard

Get details of a specific postcard by ID

get_template

Get details of a specific template

list_addresses

Use optional limit to control result count. List addresses in your Lob address book

list_bank_accounts

Use optional limit to control result count. List bank accounts in your Lob account

list_checks

Track payments, audit disbursements. List physical checks sent through Lob

list_letters

Each letter includes status, tracking number, and expected delivery date. Use optional limit to control result count. List physical letters sent through Lob. Track mailings, check delivery status, and review letter history

list_postcards

Use optional limit to control result count. List physical postcards sent through Lob

list_templates

List HTML templates for mailings

verify_us_address

Verify and standardize a US address

Example Prompts for Lob in Pydantic AI

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

"Send a letter to John Doe at 123 Main St, New York, NY 10001 with our welcome package HTML template"

"Verify if this address is deliverable: 185 Berry St, San Francisco, CA 94107"

"Send a $500 check to ABC Consulting for consulting services rendered in March"

Troubleshooting Lob MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Lob + Pydantic AI FAQ

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