How to Use the Authkey MCP in LlamaIndex

Q: How do I load Authkey message logs into a LlamaIndex vector store?

Use the McpToolSpec to fetch data using listsmshistory. This MCP integration lets you parse the output into Document objects and ingest them into your vector index using your standard LlamaIndex pipeline.

Q: Can I use LlamaIndex to query the status of an Authkey OTP?

Yes, your LlamaIndex agent can call getsmsstatus or verifyotp to check if a user successfully completed verification. You can write custom queries that analyze these verification rates over time.

Q: How do I verify that the server is online before running an indexing job?

You can have your agent call checkauthkeystatus at the start of your script. This verifies the gateway is reachable before you attempt to pull records or send messages.

Index your Authkey communication logs directly into LlamaIndex to query delivery trends and search message histories.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Authkey MCP to LlamaIndex

Create your Vinkius account to connect Authkey 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 Authkey with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live messaging logs into LlamaIndex RAG

Turn your communication data into a searchable knowledge base by calling `list_sms_history`. Your agent can pull recent messages and index them directly into a vector store. This lets you run semantic searches over what was sent to users. Instead of digging through raw database rows, you can ask your agent questions about delivery patterns. It queries the indexed logs to give you answers grounded in actual communication history.

Real-time status checks for indexed communications

Keep your index accurate by updating the delivery status of sent messages using `get_sms_status`. The agent uses this tool along with `get_email_status` to fetch the latest state of pending dispatches. Once it grabs the fresh status, it updates the corresponding document in your vector index. You can trust that your RAG application is always querying up-to-date delivery records.

Automated template selection via MCP Server tools

Let your agent choose the right message format based on user context by calling `list_templates`. The agent retrieves your approved templates and matches them against the user's query. Once the best template is matched, the agent can immediately trigger `send_sms` or `send_email` using the structured format. This prevents formatting errors and speeds up user notifications.

Setup guide

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

Use the McpToolSpec to fetch data using `list_sms_history`. This MCP integration lets you parse the output into Document objects and ingest them into your vector index using your standard LlamaIndex pipeline.

Yes, your LlamaIndex agent can call `get_sms_status` or `verify_otp` to check if a user successfully completed verification. You can write custom queries that analyze these verification rates over time.

Yes, the MCP client supports async execution. Your LlamaIndex agent can call tools like `send_bulk_sms` asynchronously, keeping your main application loop fast and responsive.

You can have your agent call `check_authkey_status` at the start of your script. This verifies the gateway is reachable before you attempt to pull records or send messages.

All transmission data, including OTP codes and SMS logs, is processed in memory inside our secure MCP sandbox. No message content or phone numbers are ever stored on Vinkius disk drives, ensuring your communication logs remain strictly private.

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