Manage AdGuard Home through AI assistants
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add mcp-adguard-home -- npx -y @samik081/mcp-adguard-home{
"mcpServers": {
"mcp-adguard-home": {
"command": "npx",
"args": ["-y", "@samik081/mcp-adguard-home"],
"env": {
"ADGUARD_URL": "<adguard_url>",
"ADGUARD_USERNAME": "<adguard_username>",
"ADGUARD_PASSWORD": "<adguard_password>"
}
}
}
}ADGUARD_URLADGUARD_USERNAMEADGUARD_PASSWORDMCP Servers overview
[](https://www.npmjs.com/package/@samik081/mcp-adguard-home)
[](https://ghcr.io/samik081/mcp-adguard-home)
[](https://opensource.org/licenses/MIT)
[](https://nodejs.org)
# MCP AdGuard Home
MCP server for [AdGuard Home](https://adguard.com/pl/adguard-home/overview.html). Manage DNS filtering, clients, DHCP, rewrites, and more through natural language in Cursor, Claude Code, and Claude Desktop.
## Features
- **65 tools** across **16 categories** covering the complete AdGuard Home API
- **Read-only mode** via `ADGUARD_ACCESS_TIER=read-only` for safe monitoring
- **Category filtering** via `ADGUARD_CATEGORIES` to expose only the tools you need
- **Zero HTTP dependencies** -- uses native `fetch` (Node.js 22+)
- **Docker images** for `linux/amd64` and `linux/arm64` on [GHCR](https://ghcr.io/samik081/mcp-adguard-home)
- **Remote MCP** via HTTP transport (`MCP_TRANSPORT=http`) using the Streamable HTTP protocol
- **TypeScript/ESM** with full type safety
## API Compatibility
Tested with AdGuard Home **v0.107.76**.
## Quick Start
Run the server directly with npx:
```bash
ADGUARD_URL="http://your-adguard-ip:3000" \
ADGUARD_USERNAME="your-username" \
ADGUARD_PASSWORD="your-password" \
npx -y @samik081/mcp-adguard-home
```
The server validates your AdGuard Home connection on startup and fails immediately with a clear error if credentials are missing or invalid.
### Docker
Run with Docker (stdio transport, same as npx):
```bash
docker run --rm -i \
-e ADGUARD_URL=http://your-adguard-ip:3000 \
-e ADGUARD_USERNAME=your-username \
-e ADGUARD_PASSWORD=your-password \
ghcr.io/samik081/mcp-adguard-home
```
To run as a remote MCP server with HTTP transport:
```bash
docker run -d -p 3000:3000 \
-e MCP_TRANSPORT=http \
-e ADGUARD_URL=http://your-adguard-ip:3000 \
-e ADGUARD_USERNAME=your-username \
-e ADGUARD_PASSWORD=your-password \
ghcr.io/samik081/mcp-adguard-home
```
The MCP endpoint is available at `http://localhost:3000` and a health check at `http://localhost:3000/health`.
## Configuration
**Claude Code CLI (recommended):**
```bash
# Using npx
claude mcp add --transport stdio adguard-home \
--env ADGUARD_URL=http://your-adguard-ip:3000 \
--env ADGUARD_USERNAME=your-username \
--env ADGUARD_PASSWORD=your-password \
-- npx -y @samik081/mcp-adguard-home
# Using Docker
claude mcp add --transport stdio adguard-home \
--env ADGUARD_URL=http://your-adguard-ip:3000 \
--env ADGUARD_USERNAME=your-username \
--env ADGUARD_PASSWORD=your-password \
-- docker run --rm -i ghcr.io/samik081/mcp-adguard-home
# Using remote HTTP (connect to a running Docker container or HTTP server)
claude mcp add --transport http adguard-home http://localhost:3000
```
**JSON config** (works with Claude Code `.mcp.json`, Claude Desktop `claude_desktop_config.json`, Cursor `.cursor/mcp.json`):
```json
{
"mcpServers": {
"adguard-home": {
"command": "npx",
"args": ["-y", "@samik081/mcp-adguard-home"],
"env": {
"ADGUARD_URL": "http://your-adguard-ip:3000",
"ADGUARD_USERNAME": "your-username",
"ADGUARD_PASSWORD": "your-password"
}
}
}
}
```
**Docker (stdio):**
```json
{
"mcpServers": {
"adguard-home": {
"command": "docker",
"args": ["run", "--rm", "-i",
"-e", "ADGUARD_URL=http://your-adguard-ip:3000",
"-e", "ADGUARD_USERNAME=your-username",
"-e", "ADGUARD_PASSWORD=your-password",
"ghcr.io/samik081/mcp-adguard-home"
]
}
}
}
```
**Remote MCP** (connect to a running Docker container or HTTP server):
```json
{
"mcpServers": {
"adguard-home": {
"type": "streamable-http",
"url": "http://localhost:3000"
}
}
}
```
## Access Tiers
Control which tools are available using the `ADGUARD_ACCESS_TIER` environment variable:
| Tier | Tools | Description |
|------|-------|-------------|
| `full` (default) | 65 | Read and write -- full control |
| `read-only` | 29 | Read only -- safe for monitoring, no state changes |
- **full**: All 65 tools. Includes configuration changes, adding/removing filters, clearing logs, and all destructive operations.
- **read-only**: 29 tools. Status, configuration viewing, and query log reading only. No state changes.
Tools that are not available in your tier are not registered with the MCP server. They will not appear in your AI tool's tool list, keeping the context clean.
## Environment Variables
| Variable | Required | Default | Description |
|----------|----------|---------|-------------|
| `ADGUARD_URL` | Yes | -- | AdGuard Home base URL (e.g., `http://192.168.1.1:3000`) |
| `ADGUARD_USERNAME` | Yes | -- | Admin username |
| `ADGUARD_PASSWORD` | Yes | -- | Admin password |
| `ADGUARD_ACCESS_TIER` | No | `full` | `read-only` for read-only tools only, `full` for all tools |
| `ADGUARD_CATEGORIES` | No | *(all)* | Comma-separated category allowlist (e.g., `dns,filtering,stats`) |
| `ADGUARD_TOOL_BLACKLIST` | No | *(none)* | Comma-separated list of tool names to exclude (e.g., `dns_clear_cache,stats_reset`) |
| `ADGUARD_TOOL_WHITELIST` | No | *(none)* | Comma-separated list of tool names to force-include, bypassing access tier and category filters |
| `DEBUG` | No | `false` | Enable debug logging to stderr |
| `MCP_TRANSPORT` | No | `stdio` | Transport mode: `stdio` (default) or `http` |
| `MCP_PORT` | No | `3000` | HTTP server port (only used when `MCP_TRANSPORT=http`) |
| `MCP_HOST` | No | `0.0.0.0` | HTTP server bind address (only used when `MCP_TRANSPORT=http`) |
| `MCP_SESSION_IDLE_TIMEOUT` | No | `1800` | Seconds of inactivity after which an HTTP session is closed and its memory released (sessions with a connected SSE stream are never closed). `0` disables. Only used when `MCP_TRANSPORT=http` |
| `MCP_EXCLUDE_TOOL_TITLES` | No | `false` | Set `true` to omit tool titles from registration (saves tokens) |
### Available Categories
`global`, `dns`, `querylog`, `stats`, `filtering`, `safebrowsing`, `parental`, `safesearch`, `clients`, `dhcp`, `rewrites`, `tls`, `blocked_services`, `access`, `install`, `mobile_config`
## Tools
mcp-adguard-home provides 65 tools organized by category. Each tool's Access column shows the minimum tier required: `read-only` (available in both tiers) or `full` (requires `full` tier). The Hints column shows tool behavior: `read-only` (no state changes), `destructive` (modifies existing state), `idempotent` (same result if called twice).
<details>
<summary>Global (6 tools)</summary>
| Tool | Description | Access | Hints |
|------|-------------|--------|-------|
| `global_get_status` | Retrieve server status including version, DNS addresses, protection state, and ports | read-only | read-only, idempotent |
| `global_get_profile` | Retrieve user profile (name, language, theme) | read-only | read-only, idempotent |
| `global_check_version` | Check for AdGuard Home updates and compare with current version | read-only | read-only, idempotent |
| `global_set_protection` | Enable or disable DNS protection globally, with optional duration for temporary disable | full | destructive, idempotent |
| `global_update_profile` | Update user profile settings (name, language, theme) | full | destructive, idempotent |
| `global_begin_update` | Initiate an AdGuard Home software update | full | destructive |
</details>
<details>
<summary>DNS (4 tools)</summary>
| Tool | Description | Access | Hints |
|------|-------------|--------|-------|
| `dns_get_info` | Retrieve full DNS configuration including upstreams, cache settings, blocking mode, and DNSSEC | read-only | read-only, idempotent |
| `dns_test_upstream` | Test upstream DNS server configuration to verify servers are reachable | read-only | read-only, idempotent |
| `dns_set_config` | Update DNS server configuration (20 optional fields for partial update) | full | destructive, idempotent |
| `dns_clear_cache` | Clear the DNS resolver cache | full | destructive, idempotent |
</details>
<details>
<summary>Query Log (4 tools)</summary>
| Tool | Description | Access | Hints |
|------|-------------|--------|-------|
| `querylog_get` | Search DNS query log with optional filtering by reason or response status, search term, and pagination | read-only | read-only, idempotent |
| `querylog_get_config` | Retrieve query log configuration settings | read-only | read-only, idempotent |
| `querylog_set_config` | Update query log configuration (enabled, interval, anonymization) | full | destructive, idempotent |
| `querylog_clear` | Clear the entire DNS query log | full | destructive, idempotent |
</details>
<details>
<summary>Statistics (4 tools)</summary>
| Tool | Description | Access | Hints |
|------|-------------|--------|-------|
| `stats_get` | Retrieve DNS statistics including top domains, blocked counts, and client activity | read-only | read-only, idempotent |
| `stats_get_config` | Retrieve statistics configuration settings | read-only | read-only, idempotent |
| `stats_reset` | Reset all DNS statistics | full | destructive, idempotent |
| `stats_set_config` | Update statistics configuration (enabled, interval, ignored domains) | full | destructive, idempotent |
</details>
<details>
<summary>Filtering (8 tools)</summary>
| Tool | Description | Access | Hints |
|------|-------------|--------|-------|
| `filtering_get_status` | Retrieve filtering configuration including blocklists, allowlists, and user rules | read-only | read-only, idempotent |
| `filtering_check_host` | Test whether a hostname would be blocked by current filtering rules | read-only | read-only, idempotent |
| `filtering_set_config` | Update global filtering configuration (enabled statWhat people ask about mcp-adguard-home
What is Samik081/mcp-adguard-home?
+
Samik081/mcp-adguard-home is mcp servers for the Claude AI ecosystem. Manage AdGuard Home through AI assistants It has 5 GitHub stars and its last recorded update is dated 2026-09-02.
How do I install mcp-adguard-home?
+
You can install mcp-adguard-home by cloning the repository (https://github.com/Samik081/mcp-adguard-home) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is Samik081/mcp-adguard-home safe to use?
+
Our security agent has analyzed Samik081/mcp-adguard-home and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains Samik081/mcp-adguard-home?
+
Samik081/mcp-adguard-home is maintained by Samik081. The last recorded GitHub activity is dated 2026-09-02, with 0 open issues.
Are there alternatives to mcp-adguard-home?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy mcp-adguard-home to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/samik081-mcp-adguard-home)<a href="https://claudewave.com/repo/samik081-mcp-adguard-home"><img src="https://claudewave.com/api/badge/samik081-mcp-adguard-home" alt="Featured on ClaudeWave: Samik081/mcp-adguard-home" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!