How to Use the AdGuard Home MCP in LlamaIndex

Q: How does LlamaIndex prevent hallucinations when managing AdGuard Home?

LlamaIndex forces the agent to call getdnsinfo and getfilteringstatus first. This grounds the agent's decisions in your actual network configuration rather than guesswork.

Q: Can I search blocked services using semantic queries?

Yes. The agent fetches the list using listblockedservices and indexes the names. You can then ask which services are active and update them with updateblockedservices.

Query, index, and update your AdGuard Home network rules using LlamaIndex RAG pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AdGuard Home MCP to LlamaIndex

Create your Vinkius account to connect AdGuard Home 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 AdGuard Home with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic Search Over Network DNS Logs

The `get_query_log` tool converts raw network outputs into searchable knowledge inside LlamaIndex. Your agent pulls data using the tool and indexes the entries into a vector store. You can then ask natural language questions about which local IPs made suspicious requests. Instead of digging through raw text, you query your indexed database. The system connects log trends to real-world context, helping you spot anomalies without manual filtering.

Grounded Network Configuration with LlamaIndex MCP Server

Using `get_dns_info` helps you avoid hallucinations when modifying DNS records. The agent reads your current network state via the tool and `list_rewrites` before suggesting any changes. It uses this live context to verify that your proposed configurations do not conflict with active settings. When you need to add a rule, the agent runs `add_rewrite` only after verifying the host isn't already mapped. This prevents routing loops and keeps your configuration clean.

Knowledge-Backed Client Management

The `list_clients` tool lets you manage your network inventory by indexing client behavior. The agent calls the tool and `search_clients` to build an active profile of every device on your LAN. If a device behaves oddly, the agent checks its profile against past logs. It can then use `add_static_lease` to isolate the device or `set_user_rules` to restrict its access.

Setup guide

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

Install llama-index-tools-mcp and load the MCP tool spec. Use `get_query_log` to fetch raw DNS activity, then feed those documents directly into your vector index.

Yes, your pipeline can query the vector index for recurring threats, then call `add_filter_url` to block the malicious domains across your network.

LlamaIndex forces the agent to call `get_dns_info` and `get_filtering_status` first. This grounds the agent's decisions in your actual network configuration rather than guesswork.

Yes. The agent fetches the list using `list_blocked_services` and indexes the names. You can then ask which services are active and update them with `update_blocked_services`.

No, all DNS query logs and client IP lists fetched via the MCP Server remain inside your local runtime. Vinkius executes the connector in a secure sandbox, preventing external leaks of your network topology.

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