How to Use the Handwrytten MCP in LlamaIndex

Q: How do I add the Handwrytten MCP Server to my LlamaIndex pipeline?

Install llama-index-tools-mcp and initialize the BasicMCPClient. Wrap it in a McpToolSpec and convert it to a tool list to give your FunctionAgent direct access to the physical mailing tools.

Q: Can LlamaIndex search through my Handwrytten templates?

Yes, LlamaIndex indexes the output of listtemplates into a vector store. This lets your agent perform semantic searches to find the most relevant template for a customer's specific situation.

Q: How does LlamaIndex prevent hallucinations when checking Handwrytten order statuses?

By querying getorder and listorders directly, the agent grounds its responses in real-time API data. It reads the actual tracking status instead of guessing or predicting when a card was shipped.

Q: Can I use LlamaIndex to manage my Handwrytten address book?

Your agent can query listaddressbook to retrieve recipient details. This data can be combined with other indexed documents to ensure you are mailing the correct physical address.

Index physical mail history into semantic vector stores using LlamaIndex and this Handwrytten 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 Handwrytten MCP to LlamaIndex

Create your Vinkius account to connect Handwrytten 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 Handwrytten with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Handwrytten MCP Server cards for RAG search

The `list_cards` tool exposes your entire Handwrytten stationery inventory directly to LlamaIndex so it can be indexed into vector stores for semantic search. Your LlamaIndex RAG pipeline can search through card descriptions and categories retrieved from `list_categories` to find the exact visual style that matches a customer's profile. This turns static physical assets from Handwrytten into queryable LlamaIndex nodes. When your LlamaIndex agent needs to send a card, it queries this local vector index instead of hitting the Handwrytten API repeatedly, saving token costs and reducing execution latency.

Query past orders using semantic search

The `list_orders` tool feeds historical Handwrytten mailing data directly into your LlamaIndex document store. This allows your LlamaIndex agent to answer questions about past physical campaigns, matching customer names from `list_address_book` with the exact Handwrytten messages sent in previous months. Instead of writing complex database queries, you ask your LlamaIndex agent when a specific customer was last mailed via Handwrytten. The LlamaIndex retriever pulls the actual order details via `get_order`, grounding the response in real Handwrytten API data rather than hallucinated dates.

Ground automated card generation in actual templates

The `list_templates` tool lets LlamaIndex extract your pre-written Handwrytten messages and store them as context for your generation pipelines. When creating a new physical note via `send_card`, the LlamaIndex framework injects these templates into the LLM prompt as reference material. This ensures your automated LlamaIndex handwriting campaigns stay on-brand with Handwrytten standards. The LlamaIndex agent verifies your available funds with `get_credit_balance` and matches the template style to the target font retrieved from `list_fonts` before queuing the physical Handwrytten mail.

Setup guide

Set up Handwrytten 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 Handwrytten 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 Handwrytten tools.",
)
response = await agent.run("List recent Handwrytten 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 Handwrytten. 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 Handwrytten 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 Handwrytten MCP in LlamaIndex

Install `llama-index-tools-mcp` and initialize the `BasicMCPClient`. Wrap it in a `McpToolSpec` and convert it to a tool list to give your `FunctionAgent` direct access to the physical mailing tools.

Yes, LlamaIndex indexes the output of `list_templates` into a vector store. This lets your agent perform semantic searches to find the most relevant template for a customer's specific situation.

By querying `get_order` and `list_orders` directly, the agent grounds its responses in real-time API data. It reads the actual tracking status instead of guessing or predicting when a card was shipped.

Your agent can query `list_address_book` to retrieve recipient details. This data can be combined with other indexed documents to ensure you are mailing the correct physical address.

Recipient mailing addresses and physical names are processed in memory to execute `send_card` and are never persisted in the LlamaIndex vector store unless you explicitly configure a local storage index. All transmission is encrypted end-to-end through the secure MCP gateway to Handwrytten.

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