How to Use the Lob MCP in LlamaIndex

Q: Can LlamaIndex query my Lob bank account list?

Yes, the agent can call listbankaccounts to retrieve your registered accounts. LlamaIndex indexes this metadata, allowing you to ask which bank account is configured for physical check runs.

Q: How does LlamaIndex handle search queries about physical postcards sent through Lob?

The agent uses listpostcards to pull sent history and indexes the resulting payloads. When you ask about a specific campaign, LlamaIndex performs a semantic search over those indexed postcards to locate the tracking details.

Q: Can I filter which tools are exposed to my agent?

Yes, you can use the allowedtools filter when setting up the tool spec. This lets you expose safe tools like verifyusaddress while blocking sensitive tools like createcheck.

Index your physical mail history and verify delivery addresses inside your LlamaIndex knowledge base using the Lob MCP Server.

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 LlamaIndex

Create your Vinkius account to connect Lob to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index physical mail records using this MCP Server

The `list_letters` tool pulls your entire Lob physical mailing history, including delivery statuses and recipient names. LlamaIndex takes this raw data and indexes it into a vector store so you can query your physical mail history using natural language. Instead of digging through some database, just ask your LlamaIndex agent when a specific Lob letter was sent. The LlamaIndex RAG pipeline searches the indexed output of `get_letter` to find the exact delivery date.

Verify addresses before indexing them in LlamaIndex

The `verify_us_address` tool standardizes and validates physical locations before they enter your LlamaIndex database. LlamaIndex uses this clean address data to build a highly accurate semantic index of your customer base. By running `autocomplete_us_address` first, you prevent duplicate or broken Lob records from corrupting your LlamaIndex vector index. Your LlamaIndex search queries remain fast because the underlying address data is clean.

Search your LlamaIndex mail templates semantically

The `list_templates` tool retrieves all your reusable HTML designs from your Lob account. LlamaIndex indexes these templates, allowing your agent to find the correct HTML layout based on the context of the customer's support ticket. When a customer requests a physical statement, the LlamaIndex agent queries the index using `get_template` to locate the exact Lob layout. It's a clean way to eliminate manual template selection and ensure the right design is used for `create_letter`.

Setup guide

Set up Lob MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Lob MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Lob tools.",
)
response = await agent.run("List recent Lob data")

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 LlamaIndex

Install llama-index-tools-mcp and initialize the BasicMCPClient with your Vinkius endpoint. Convert it to a tool specification using McpToolSpec and pass it to your LlamaIndex FunctionAgent.

Yes, the agent can call list_bank_accounts to retrieve your registered accounts. LlamaIndex indexes this metadata, allowing you to ask which bank account is configured for physical check runs.

The agent uses list_postcards to pull sent history and indexes the resulting payloads. When you ask about a specific campaign, LlamaIndex performs a semantic search over those indexed postcards to locate the tracking details.

Yes, you can use the allowed_tools filter when setting up the tool spec. This lets you expose safe tools like verify_us_address while blocking sensitive tools like create_check.

Your recipient names and street addresses are processed in memory within Vinkius's zero-trust sandbox. The framework only indexes the data you explicitly query, and the underlying API tokens are never exposed to the LLM.

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