Bring Dns Filtering
to OpenAI Agents SDK
Learn how to connect AdGuard Home to OpenAI Agents SDK and start using 23 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the AdGuard Home MCP Server?
Connect your AdGuard Home instance to any AI agent and take full control of your network-wide privacy and security through natural conversation.
What you can do
- Server Status — Monitor server health, active ports, protection states, and version information in real-time.
- Protection Control — Toggle global filtering, safe browsing, and parental controls on or off, with optional timed durations.
- DNS Configuration — View and update upstream DNS servers, bootstrap settings, and cache parameters (TTL, size, and optimistic caching).
- Filter Management — Add new blocklist or allowlist URLs and manage custom user-defined filtering rules.
- Client Insights — List and search for persistent or runtime clients, and configure specific security settings for individual devices.
- Host Auditing — Instantly check if a specific domain is being filtered or blocked for a particular client.
How it works
- Subscribe to this server
- Enter your AdGuard Home Base URL and credentials (Username/Password)
- Start managing your network security from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Home Lab Enthusiasts — monitor and tweak your network-wide ad blocker without opening the web dashboard.
- Network Administrators — quickly update upstream DNS providers or check why a specific host is being blocked.
- Privacy-focused Users — manage custom filtering rules and client-specific protections through simple voice or text commands.
Built-in capabilities (23)
Add a new client
Add a new filter URL
Add a DNS rewrite
Add a DHCP static lease
Check if a host is filtered
Configure TLS settings
Get DHCP server status
Get DNS configuration info
Get filtering status and lists
Get DNS query log
Get query log configuration
Get DNS query statistics
Get AdGuard Home server status
Get TLS configuration status
List all available blocked services
List all clients
List DNS rewrites
Search for clients
Update DNS settings
globally. Enable or disable protection globally
Set custom user filtering rules
Update blocked services schedule
Update query log configuration
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 23 tools from AdGuard Home through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries AdGuard Home, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
AdGuard Home in OpenAI Agents SDK
AdGuard Home and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect AdGuard Home to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for AdGuard Home in OpenAI Agents SDK
The AdGuard Home MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 23 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
AdGuard Home for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the AdGuard Home MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I check if a specific website is being blocked for a specific client?
Yes, use the check_host tool. Provide the domain name and optionally the client IP to see if it's filtered and which rule is responsible.
Is it possible to pause the ad-blocking globally for a short period?
Yes. The set_protection tool allows you to disable filtering globally. You can also specify a duration in milliseconds if you want it to re-enable automatically.
How do I add a new blocklist URL using the AI?
Simply use the add_filter_url action. You'll need to provide a name for the filter, the URL of the list, and specify if it's a whitelist or blocklist.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
Amplience
10 toolsConnect your Amplience CMS to your AI agent — query hubs, pull content, edit schemas, and deploy live items easily via chat.
Infisical
9 toolsManage secrets infrastructure via AI — list, create, update, and audit secrets across environments with end-to-end encryption.
Swan
9 toolsEmpowers algorithmic control over European Bank Accounts. Execute SEPA transfers and manage Virtual Corporate Cards programmatically.
RocketReach
12 toolsFind accurate contact information for professionals and companies with a database of verified emails and direct phone numbers.