adguard-home-agent 0.15.0

AdGuard Home MCP Server for Agentic AI!

Adguard Home Agent

CLI or API | MCP | Agent

Version: 0.15.0

---

Overview

Adguard Home Agent is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with AdGuard Home MCP Server for Agentic AI!.

---

Key Features

• Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules.
• Enterprise-Grade Security: Comprehensive support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
• Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
• Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.

---

CLI or API

This agent wraps the AdGuard Home MCP Server for Agentic AI! API. You can interact with it programmatically or via its integrated execution entrypoints.

Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.

---

MCP

This server utilizes dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

Available MCP Tools

Tool Module	Toggle Env Var	Enabled by Default	Description & Nested Methods
System	SYSTEMTOOL	True	Manage adguard home system operations. Action-routed methods: get_version, set_protection, clear_cache.
Access	ACCESSTOOL	True	Manage adguard home access operations. Action-routed methods: get_access_list, set_access_list.
Blocked Services	BLOCKED_SERVICESTOOL	True	Manage adguard home blocked services operations. Action-routed methods: get_blocked_services_list, get_all_blocked_services, update_blocked_services.
Filtering	FILTERINGTOOL	True	Manage adguard home filtering operations. Action-routed methods: set_filtering_rules, check_host_filtering, set_filter_url_params, get_filtering_status, set_filtering_config, add_filter_url, remove_filter_url, refresh_filters.
Clients	CLIENTSTOOL	True	Manage adguard home clients operations. Action-routed methods: list_clients, search_clients, add_client, update_client, delete_client.
Profile	PROFILETOOL	True	Manage adguard home profile operations. Action-routed methods: get_profile, update_profile.
Dhcp	DHCPTOOL	True	Manage adguard home dhcp operations. Action-routed methods: get_dhcp_status, get_dhcp_interfaces, set_dhcp_config, find_active_dhcp, add_dhcp_static_lease, remove_dhcp_static_lease, update_dhcp_static_lease, reset_dhcp, reset_dhcp_leases.
Settings	SETTINGSTOOL	True	Manage adguard home settings operations. Action-routed methods: get_parental_status, enable_parental_control, disable_parental_control, get_safebrowsing_status, enable_safebrowsing, disable_safebrowsing, get_safesearch_status.
Query Log	QUERY_LOGTOOL	True	Manage adguard home query log operations. Action-routed methods: get_query_log, clear_query_log.
Rewrites	REWRITESTOOL	True	Manage adguard home rewrites operations. Action-routed methods: list_rewrites, add_rewrite, delete_rewrite, update_rewrite, get_rewrite_settings, update_rewrite_settings.
Tls	TLSTOOL	True	Manage adguard home tls operations. Action-routed methods: get_tls_status, configure_tls, validate_tls.
Mobile	MOBILETOOL	True	Manage adguard home mobile operations. Action-routed methods: get_doh_mobile_config, get_dot_mobile_config.
Stats	STATSTOOL	True	Manage adguard home stats operations. Action-routed methods: get_stats, reset_stats, get_stats_config, set_stats_config.
Dns	DNSTOOL	True	Manage adguard home dns operations. Action-routed methods: get_dns_info, set_dns_config, test_upstream_dns.

Detailed tool schemas, parameter shapes, and validation constraints are preserved in docs/mcp.md.

MCP Configuration Examples

stdio Transport (Recommended for local IDEs e.g., Cursor, Claude Desktop)

Configure your IDE's mcp.json to launch the MCP server via uvx:

{
  "mcpServers": {
    "adguard-home-agent": {
      "command": "uvx",
      "args": [
        "--from",
        "adguard-home-agent",
        "adguard-mcp"
      ],
      "env": {
        "ADGUARD_HOST": "your_adguard_host_here",
        "ADGUARD_API_KEY": "your_adguard_api_key_here",
        "ADGUARD_DEFAULT_ADMIN_USER": "your_adguard_default_admin_user_here",
        "ADGUARD_DEFAULT_ADMIN_PASS": "your_adguard_default_admin_pass_here",
        "LLM_ROUTER_MODEL": "your_llm_router_model_here",
        "LLM_AGENT_MODEL": "your_llm_agent_model_here",
        "GRAPH_ROUTER_TIMEOUT": "your_graph_router_timeout_here",
        "GRAPH_VERIFIER_TIMEOUT": "your_graph_verifier_timeout_here"
      }
    }
  }
}

Streamable-HTTP Transport (Recommended for production deployments)

Configure your client's mcp.json to launch the Streamable-HTTP server via uvx with explicit host and port definition:

{
  "mcpServers": {
    "adguard-home-agent": {
      "command": "uvx",
      "args": [
        "--from",
        "adguard-home-agent",
        "adguard-mcp"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "ADGUARD_HOST": "your_adguard_host_here",
        "ADGUARD_API_KEY": "your_adguard_api_key_here",
        "ADGUARD_DEFAULT_ADMIN_USER": "your_adguard_default_admin_user_here",
        "ADGUARD_DEFAULT_ADMIN_PASS": "your_adguard_default_admin_pass_here",
        "LLM_ROUTER_MODEL": "your_llm_router_model_here",
        "LLM_AGENT_MODEL": "your_llm_agent_model_here",
        "GRAPH_ROUTER_TIMEOUT": "your_graph_router_timeout_here",
        "GRAPH_VERIFIER_TIMEOUT": "your_graph_verifier_timeout_here"
      }
    }
  }
}

Alternatively, connect to a pre-deployed remote or local Streamable-HTTP instance:

{
  "mcpServers": {
    "adguard-home-agent": {
      "url": "http://localhost:8000/adguard-home-agent/mcp"
    }
  }
}

Deploying the Streamable-HTTP server via Docker:

docker run -d \
  --name adguard-home-agent-mcp \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e PORT=8000 \
  -e ADGUARD_HOST="your_value" \
  -e ADGUARD_API_KEY="your_value" \
  -e ADGUARD_DEFAULT_ADMIN_USER="your_value" \
  -e ADGUARD_DEFAULT_ADMIN_PASS="your_value" \
  -e LLM_ROUTER_MODEL="your_value" \
  -e LLM_AGENT_MODEL="your_value" \
  -e GRAPH_ROUTER_TIMEOUT="your_value" \
  -e GRAPH_VERIFIER_TIMEOUT="your_value" \
  knucklessg1/adguard-home-agent:latest

---

Agent

This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts seamlessly with the Agent Web UI (AG-UI) and Terminal interface.

Running the Agent CLI

To start the interactive command-line agent:

# Set credentials
export ADGUARD_HOST="your_value"
export ADGUARD_API_KEY="your_value"
export ADGUARD_DEFAULT_ADMIN_USER="your_value"
export ADGUARD_DEFAULT_ADMIN_PASS="your_value"
export LLM_ROUTER_MODEL="your_value"
export LLM_AGENT_MODEL="your_value"
export GRAPH_ROUTER_TIMEOUT="your_value"
export GRAPH_VERIFIER_TIMEOUT="your_value"

# Run the agent server
adguard-agent --provider openai --model-id gpt-4o

Docker Compose Orchestration

The following docker/agent.compose.yml configures the Agent, Web UI, and Terminal Interface together:

version: '3.8'

services:
  adguard-home-agent-mcp:
    image: knucklessg1/adguard-home-agent:latest
    container_name: adguard-home-agent-mcp
    hostname: adguard-home-agent-mcp
    restart: always
    env_file:
      - ../.env
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=streamable-http
    ports:
      - "8000:8000"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

  adguard-home-agent-agent:
    image: knucklessg1/adguard-home-agent:latest
    container_name: adguard-home-agent-agent
    hostname: adguard-home-agent-agent
    restart: always
    depends_on:
      - adguard-home-agent-mcp
    env_file:
      - ../.env
    command: [ "adguard-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9012
      - MCP_URL=http://adguard-home-agent-mcp:8000/mcp
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9012:9012"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9012/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

Detailed graph node architecture explanations, custom skill configurations, and agentic trace guides are available in docs/agent.md.

---

Security & Governance

Built directly upon the enterprise-ready agent-utilities core, standard security parameters are fully supported:

Access Control & Policy Enforcement

• Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports none, local embedded (mcp_policies.json), or centralized remote modes.
• OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
• Scoped Credentials: Execution context runs restricted to the specific caller identity.

Runtime Security Grid

Feature	Functionality	Enablement
Tool Guard	Sensitivity inspection with human-in-the-loop validation	Enabled by default
Prompt Injection Defense	Input scanning, repetition monitoring, and recursive loop blocks	Enabled by default
Context Safety Guard	Stuck-loop detectors and contextual overflow preemptive alerts	Enabled by default

---

Installation

Install the Python package locally:

# Using uv (highly recommended)
uv pip install adguard-home-agent[all]

# Using standard pip
python -m pip install adguard-home-agent[all]

---

Repository Owners

---

Contribute

Contributions are welcome! Please ensure code quality by executing local checks before submitting pull requests:

• Format code using ruff format .
• Lint code using ruff check .
• Validate type-safety with mypy .
• Execute test suites using pytest