Media Downloader

CLI or API | MCP

Version: 4.4.5

Documentation — Installation, deployment, and usage across the CLI, Python API, MCP, and A2A agent interfaces are maintained in the official documentation.

---

Overview

Media Downloader is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with Download audio/videos from the internet! Host an MCP Server for Agentic AI to download videos!.

---

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: Complete 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 Download audio/videos from the internet! Host an MCP Server for Agentic AI to download videos! API. The operator 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 use dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

Available MCP Tools

Condensed action-routed tools (MCP_TOOL_MODE=condensed)

MCP Tool	Toggle Env Var	Description
build_watch_skill	—	Write a video-built skill, or append another video's findings to one.
download_media	—	Download video or audio from supported sites (YouTube, Rumble, etc.).
list_watch_skills	—	List video-built skills under a root and the videos each already has.
watch_media	—	Watch a video: download it with captions and extract key frames.

Verbose 1:1 API-mapped tools (MCP_TOOL_MODE=verbose or both)

MCP Tool	Toggle Env Var	Description
media_downloader_download_all	MEDIA_DOWNLOADERTOOL	Invoke the download_all operation.
media_downloader_download_video	MEDIA_DOWNLOADERTOOL	Invoke the download_video operation.
media_downloader_get_channel_videos	MEDIA_DOWNLOADERTOOL	Invoke the get_channel_videos operation.
media_downloader_watch	MEDIA_DOWNLOADERTOOL	Download a video with its captions and extract scene-change key frames.

4 action-routed tool(s) · 7 verbose 1:1 tool(s). Each is enabled unless its <DOMAIN>TOOL toggle is set false; MCP_TOOL_MODE selects the surface (intent default — the six verb-tools, granular set loaded on demand · condensed action-routed · verbose 1:1 · both). Auto-generated — do not edit.

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

Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows the operator to restrict the set of exposed tools to prevent blowing up the LLM's context window.

The operator can configure tool filtering via multiple input channels:

• CLI Arguments: Pass --tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.
• Environment Variables: Define standard environment variables:
  • MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS
  • MCP_ENABLED_TAGS / MCP_DISABLED_TAGS
• HTTP SSE Request Headers: Pass custom headers during transport initialization:
  • x-mcp-enabled-tools / x-mcp-disabled-tools
  • x-mcp-enabled-tags / x-mcp-disabled-tags
• HTTP SSE Request Query Parameters: Append query parameters directly to the operator's transport connection URL:
  • ?tools=tool1,tool2
  • ?tags=tag1

When query strings or parameters are supplied, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.

---

MCP Configuration Examples

Install the connector-focused [mcp] extra. Examples use media-downloader[mcp] to add FastMCP / FastAPI through scion-sdk; the required Scion SDK core still carries medulla[full]. The [agent-runtime] extra additionally enables model orchestration.

stdio Transport (local IDEs — Cursor, Claude Desktop, VS Code)

{
  "mcpServers": {
    "media-downloader-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "media-downloader[mcp]",
        "media-downloader-mcp"
      ],
      "env": {
        "MCP_TOOL_MODE": "intent",
        "MEDIA_DOWNLOADER_ALLOW_PRIVATE_HOSTS": "media.internal.example",
        "MEDIA_DOWNLOADER_MAX_WORKERS": "4",
        "MEDIA_DOWNLOADER_OUTPUT_ROOT": "/data/media",
        "WORKSPACE_PATH": "workspace"
      }
    }
  }
}

Runtime references require an alias-aware launcher such as Arbora. Other launchers must omit those entries and inject the resolved values through their own runtime secret boundary.

Streamable-HTTP Transport (networked / production)

{
  "mcpServers": {
    "media-downloader-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "media-downloader[mcp]",
        "media-downloader-mcp",
        "--transport",
        "streamable-http",
        "--port",
        "8000"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "127.0.0.1",
        "PORT": "8000",
        "MCP_TOOL_MODE": "intent",
        "MEDIA_DOWNLOADER_ALLOW_PRIVATE_HOSTS": "media.internal.example",
        "MEDIA_DOWNLOADER_MAX_WORKERS": "4",
        "MEDIA_DOWNLOADER_OUTPUT_ROOT": "/data/media",
        "WORKSPACE_PATH": "workspace"
      }
    }
  }
}

Alternatively, connect to a pre-deployed Streamable-HTTP instance by url:

{
  "mcpServers": {
    "media-downloader-mcp": {
      "url": "http://localhost:8000/media-downloader-mcp/mcp"
    }
  }
}

Run a reviewed container image as a least-privilege stdio child (no listener or published port):

docker run -i --rm \
  --read-only \
  --cap-drop=ALL \
  --security-opt=no-new-privileges \
  --pids-limit=256 \
  --tmpfs /tmp:rw,noexec,nosuid,nodev,size=64m \
  -e TRANSPORT=stdio \
  -e MCP_TOOL_MODE=intent \
  -e MEDIA_DOWNLOADER_ALLOW_PRIVATE_HOSTS=media.internal.example \
  -e MEDIA_DOWNLOADER_MAX_WORKERS=4 \
  -e MEDIA_DOWNLOADER_OUTPUT_ROOT=/data/media \
  -e WORKSPACE_PATH=workspace \
  registry.example.invalid/media-downloader@sha256:<digest> media-downloader-mcp

For containerized network HTTP, supply an authenticated TLS ingress (or direct server TLS), exact MCP_ALLOWED_HOSTS, and an exact trusted-proxy CIDR policy through the operator-owned deployment profile. The generator does not emit an unauthenticated non-loopback listener.

Auto-generated from the code-read env surface (MCP_TOOL_MODE + package vars) — do not edit.

Additional Deployment Options

media-downloader can run as a local stdio process or container, or behind a remote network boundary. The Deployment guide carries the detailed transport contract.

• Local container — launch a reviewed immutable image as a least-privilege stdio child with no listener or published port.
• Remote URL — connect through an operator-supplied authenticated HTTPS ingress. Keep its URL, outbound identity references, trust profile, and exact MCP_ALLOWED_HOSTS in AgentConfig.

Agent

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

Running the Agent CLI

To start the interactive command-line agent:

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

Docker Compose Orchestration

version: '3.8'

services:
  media-downloader-mcp:
    image: example/media-downloader@sha256:<digest>
    container_name: media-downloader-mcp
    hostname: media-downloader-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"

    image: example/media-downloader@sha256:<digest>
    container_name: media-downloader-agent
    hostname: media-downloader-agent
    restart: always
    depends_on:
      - media-downloader-mcp
    env_file:
      - ../.env
    command: [ "media-downloader-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9000
      - MCP_URL=http://media-downloader-mcp:8000/mcp
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9000:9000"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9000/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/deployment.md.

---

Security & Governance

Built directly upon the enterprise-ready scion-sdk 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	Feature	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

---

Environment Variables

Package environment variables

Variable	Example	Description
HOST	0.0.0.0
PORT	8000
TRANSPORT	stdio	options: stdio, streamable-http, sse
ENABLE_OTEL	True
OTEL_EXPORTER_OTLP_ENDPOINT	http://localhost:8080/api/public/otel
OTEL_EXPORTER_OTLP_PUBLIC_KEY_REF	pk-...
OTEL_EXPORTER_OTLP_SECRET_KEY_REF	sk-...
OTEL_EXPORTER_OTLP_PROTOCOL	http/protobuf
EUNOMIA_TYPE	none	options: none, embedded, remote
EUNOMIA_POLICY_FILE	mcp_policies.json
EUNOMIA_REMOTE_URL	http://eunomia-server:8000
MEDIA_DOWNLOADER_MCP_IMAGE	knucklessg1/media-downloader@sha256:<digest>	Required by the hardened compose profiles — no floating tag is assumed. Point these at an immutable digest of a reviewed image before running docker compose up.
MEDIA_DOWNLOADER_AGENT_IMAGE	knucklessg1/media-downloader@sha256:<digest>
MEDIA_DOWNLOADER_OUTPUT_ROOT	/data/media	Every download is written beneath this root; a path that escapes it is rejected. Falls back to WORKSPACE_PATH, then ~/Downloads.
WORKSPACE_PATH	workspace
MEDIA_DOWNLOADER_ALLOW_PRIVATE_HOSTS	media.internal.example	Exact hostnames allowed to resolve to a private address. Downloads are restricted to publicly routable hosts otherwise; no wildcards are accepted.
MEDIA_DOWNLOADER_MAX_WORKERS

Inherited scion-sdk variables (apply to every connector)

Variable	Example	Description
MCP_TOOL_MODE	intent	Tool surface: intent | condensed | verbose | both
MCP_ENABLED_TOOLS	—	Comma-separated tool allow-list
MCP_DISABLED_TOOLS	—	Comma-separated tool deny-list
MCP_ENABLED_TAGS	—	Comma-separated tag allow-list
MCP_DISABLED_TAGS	—	Comma-separated tag deny-list
MCP_CLIENT_AUTH	—	Outbound MCP child auth: oidc-client-credentials | basic | none
OIDC_CLIENT_ID	—	OIDC client id (service-account auth)
OIDC_CLIENT_SECRET_REF	secret://identity/oidc-client-secret	Runtime secret reference for the OIDC service account
MCP_BASIC_AUTH_USERNAME	—	HTTP Basic username (MCP_CLIENT_AUTH=basic)
MCP_BASIC_AUTH_PASSWORD_REF	secret://identity/mcp-basic-password	Runtime secret reference for HTTP Basic auth (MCP_CLIENT_AUTH=basic)
DEBUG	False	Verbose logging
PYTHONUNBUFFERED	1	Unbuffered stdout (recommended in containers)
MCP_URL	http://localhost:8000/mcp	URL of the MCP server the agent connects to
PROVIDER	—	Operator-configured LLM provider for the agent
MODEL_ID	—	Operator-configured model id for the agent
ENABLE_WEB_UI	True	Serve the AG-UI web interface

17 package + 16 inherited variable(s). Auto-generated from .env.example + the shared scion-sdk set — do not edit.

Every variable the server reads. A local template is supplied inside .env.example — copy it to .env and adjust as needed.

MCP server / transport

Variable	Description	Default
TRANSPORT	stdio, streamable-http, or sse	stdio
HOST	Bind host (HTTP transports)	0.0.0.0
PORT	Bind port (HTTP transports)	8000
MCP_TOOL_MODE	Tool surface: condensed, verbose, or both	condensed
MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS	Comma-separated tool allow/deny list	—
MCP_ENABLED_TAGS / MCP_DISABLED_TAGS	Comma-separated tag allow/deny list	—
PYTHONUNBUFFERED	Unbuffered stdout (recommended in containers)	1

Telemetry & governance

Variable	Description	Default
ENABLE_OTEL	Enable OpenTelemetry export	True
OTEL_EXPORTER_OTLP_ENDPOINT	OTLP collector endpoint	—
OTEL_EXPORTER_OTLP_PUBLIC_KEY / OTEL_EXPORTER_OTLP_SECRET_KEY	OTLP auth keys	—
OTEL_EXPORTER_OTLP_PROTOCOL	OTLP protocol (e.g. http/protobuf)	—
EUNOMIA_TYPE	Authorization mode: none, embedded, remote	none
EUNOMIA_POLICY_FILE	Embedded policy file	mcp_policies.json
EUNOMIA_REMOTE_URL	Remote Eunomia server URL	—

Agent CLI (full [agent] runtime only)

Variable	Description	Default
MCP_URL	URL of the MCP server the agent connects to	http://localhost:8000/mcp
PROVIDER	LLM provider (e.g. openai)	openai
MODEL_ID	Model id (e.g. gpt-4o)	gpt-4o
ENABLE_WEB_UI	Serve the AG-UI web interface	True

---

Installation

Pick the extra that matches what the operator want to run:

Extra	Installs	Use when
media-downloader[mcp]	Connector-focused MCP server (scion-sdk — FastMCP/FastAPI + medulla[full])	The operator only run the MCP server (smallest install / image)
media-downloader[all]	Everything (mcp + agent + logfire)	Development / both surfaces

# Connector-focused MCP server (includes the shared graph engine)
uv pip install "media-downloader[mcp]"

# Agent runtime (adds model orchestration to the shared graph engine)

# Everything (development)
uv pip install "media-downloader[all]"      # or: python -m pip install "media-downloader[all]"

Container images (:mcp)

One multi-stage docker/Dockerfile builds the MCP-only image (--target mcp):

Image tag	Build target	Contents	Entrypoint
knucklessg1/media-downloader:mcp	--target mcp	media-downloader[mcp] — connector-focused, includes medulla[full]; no model-orchestration stack	media-downloader-mcp

docker build --target mcp   -t knucklessg1/media-downloader:mcp   docker/   # connector-focused MCP server

agent (default build) with a co-located :mcp sidecar. For an immutable production digest, tag and pin the operator's own build as shown in the hardened docker run pattern above.

Knowledge-graph database (medulla)

Scion SDK core dependency (medulla[full]). The [mcp] extra keeps deployments can use the bundled engine. For production — or to share one knowledge graph across multiple agents — run medulla as its own dedicated database service and configure the runtime to use it instead of the bundled engine. Deployment recipes (single-node + Raft HA), connection configuration, and the full database architecture (with diagrams) are documented in the medulla deployment guide.

---

Documentation

The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.

Page	Contents
Installation	pip, source, extras, prebuilt Docker image
Deployment	run the MCP server, the agent server, Compose, Caddy + Technitium, env config
Usage	the MCP tools, the MediaDownloader Python API, the CLI
Overview	ecosystem role, enterprise readiness, architecture
Concepts	concept registry (CONCEPT:MDLD-*)

AGENTS.md is the canonical contributor/agent guidance.

---

Repository Owners

---

Contribute

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

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

Governed capability contract

This package ships a compact canonical skill surface with specialist procedures kept as referenced workflows. The current MCP tools, skill metadata, connector_manifest.yml, ontology, mappings, shapes, fixtures, migrations, tool-schema fingerprints, and certification metadata form one versioned capability contract. Validate them together; do not rely on stale tool names or historical per-task skill wrappers.

Runtime endpoints, credentials, certificate trust, tenant identity, retention, and observability policy are deployment inputs and are never packaged values. See Configuration, trust, and privacy before enabling a network transport, connector ingestion, Arbora delegation, or trace export.