How to Use the Lob MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK handle address autocompletion with Lob?

Yes. Your agent uses autocompleteusaddress to resolve partial user inputs into valid delivery points. You can set cacheToolsList=True to keep tool lookup times low during conversational sessions.

Q: How does the agent stop a Lob letter before it prints?

The agent calls cancelletter with the target letter ID. This operation succeeds only if the letter status is still processing, which you can check by running getletter first.

Q: What is the best way to handle template variables?

Use createtemplate to register your HTML layout with Lob. Your agent then calls createletter or createpostcard and passes a dictionary of merge variables to fill in the dynamic fields automatically.

Deploy production OpenAI Agents SDK systems that mail physical letters, checks, and postcards with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lob MCP to OpenAI Agents SDK

Create your Vinkius account to connect Lob to OpenAI Agents SDK 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 Lob with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Verify and clean US addresses before mailing

The Lob MCP Server exposes `verify_us_address` and `autocomplete_us_address` to clean up messy user inputs before they hit production. Your agent intercepts raw strings, autocompletes the partial data, and standardizes the format to prevent returned mail. Because you are running this inside the OpenAI Agents SDK, you can set up a validation guardrail that blocks the agent from calling mailing tools if the address verification step fails. This keeps your delivery rates high and stops your system from wasting budget on undeliverable mail.

Automate physical mailings directly from OpenAI Agents SDK

The `create_letter`, `create_postcard`, and `create_template` tools let your agent generate physical mail using HTML templates and custom merge variables. The agent selects the right template, populates the variables, and queues the print job. If a user changes their mind, the agent can invoke `cancel_letter` to stop production before the mail piece is printed. You can trace this entire decision tree and MCP tool execution path directly inside your OpenAI developer dashboard.

Securely issue and track physical checks

The `create_bank_account` and `create_check` tools allow your agent to register bank accounts and mail physical checks to vendors or customers. Your agent handles the routing details, sets the amount, and triggers the print queue. You can monitor these disbursements using `list_checks` and `get_check` to audit your automated financial workflows. By handing off tasks between specialized agents, you ensure one agent verifies the address while another handles the actual check issuance.

Setup guide

Set up Lob MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Lob tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Lob tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Lob tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Lob Agent",
            instructions="You have access to Lob tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Lob. 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 Lob 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 Lob MCP in OpenAI Agents SDK

Install the package and run the server using the streamable HTTP transport parameter. Pass the server instance inside the `mcp_servers` list when initializing your Agent class. The SDK automatically discovers all 21 tools.

Yes. Your agent uses `autocomplete_us_address` to resolve partial user inputs into valid delivery points. You can set `cacheToolsList=True` to keep tool lookup times low during conversational sessions.

The agent calls `cancel_letter` with the target letter ID. This operation succeeds only if the letter status is still processing, which you can check by running `get_letter` first.

Use `create_template` to register your HTML layout with Lob. Your agent then calls `create_letter` or `create_postcard` and passes a dictionary of merge variables to fill in the dynamic fields automatically.

Your recipient addresses, bank details, and letter contents run inside the Vinkius MCP Server sandbox. This keeps sensitive financial records and customer PII isolated from external network threats.

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