How to Use the Kisi MCP in LlamaIndex

Q: How does LlamaIndex prevent hallucinating Kisi lock statuses?

It uses McpToolSpec to query getlockdetails directly before answering. The agent bases its response entirely on the fresh JSON payload returned by the hardware.

Q: Can I index Kisi user lists into a vector database using LlamaIndex?

Yes, your pipeline can call listusers to ingest employee directories. LlamaIndex chunks and indexes this data, allowing you to search for permissions using natural language.

Q: Does LlamaIndex support running write operations like unlockdoor?

Yes, you can include unlockdoor in the active tool list. The agent will execute the physical unlock action when a query explicitly requires opening a door.

Index your physical security architecture into LlamaIndex to query locks and access groups with this 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 Kisi MCP to LlamaIndex

Create your Vinkius account to connect Kisi 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 Kisi with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing Access Groups for Semantic Security RAG

The `list_access_groups` and `list_role_assignments` tools allow your LlamaIndex pipeline to pull physical permission structures directly into a vector index. This lets you ask natural language questions about who can enter which room without writing SQL. The framework indexes these live configurations so your agent can query past setups. You get answers grounded in your actual Kisi database, eliminating typical model hallucinations about who has access. It just works.

Real-Time Hardware Status Indexing

The `list_locks` and `get_lock_details` tools provide the raw hardware states that LlamaIndex converts into searchable document nodes. Your system queries the live state of your doors and compares it against historical logs in your vector store. This turns physical hardware data into a dynamic knowledge base. Your agent can instantly pinpoint which locks are offline or misconfigured by comparing live tool outputs to your security blueprints. No more guessing.

Location Mapping via MCP Server Queries

The `list_places` and `get_place_details` tools feed your LlamaIndex RAG pipelines with physical geographic coordinates and office metadata. The agent maps your global office locations to find patterns in access logs. By hooking this MCP Server up to LlamaIndex, you bridge the gap between physical office layouts and your digital knowledge base. This setup cross-references these places against your internal wiki docs for unified facility management.

Setup guide

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

It uses McpToolSpec to query `get_lock_details` directly before answering. The agent bases its response entirely on the fresh JSON payload returned by the hardware.

Yes, your pipeline can call `list_users` to ingest employee directories. LlamaIndex chunks and indexes this data, allowing you to search for permissions using natural language.

Initialize the BasicMCPClient with the server URL, wrap it in McpToolSpec, and convert it using the asynchronous tool list method. Pass that list to your FunctionAgent to start querying.

Yes, you can include `unlock_door` in the active tool list. The agent will execute the physical unlock action when a query explicitly requires opening a door.

The server only processes temporary API tokens to fetch lock states and user profiles. All data is processed in memory within a zero-trust sandbox, so no physical access logs are cached or leaked.

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