How to Use the Prowlarr (Indexers) MCP in Google ADK

Q: How do I configure Prowlarr (Indexers) with the Google ADK?

Install the google-adk package. Set up your StreamableHttpServerParameters with the endpoint, wrap it in an McpToolset, and assign it to your LlmAgent tools array.

Q: Can I restrict which Prowlarr (Indexers) tools the Google ADK sees?

You can filter the exposed tools using the toolnames parameter in the toolset configuration. This prevents your Gemini agent from accidentally calling destructive tools like deleteindexer while still allowing read access.

Q: How do I handle tracker templates?

You must use getindexerschema. Prowlarr refuses generic configurations. The agent fetches the exact JSON structure for that specific torrent site before pushing the final payload.

Connect your Prowlarr instance to the Google ADK and let Gemini manage your trackers at scale.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Prowlarr (Indexers) MCP to Google ADK

Create your Vinkius account to connect Prowlarr (Indexers) to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Prowlarr (Indexers) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Massive context analysis via MCP Server

The `prowlarr-indexers-mcp` MCP Server gives Gemini direct read and write access to your media indexers. You wrap the endpoint URL in `McpToolset` and pass it directly to your `LlmAgent` initialization. Because Gemini handles massive context windows, you can dump the entire output of `list_indexers` and `get_indexer_status` into a single prompt. The agent analyzes the health of hundreds of trackers simultaneously without chunking the data.

BigQuery integration for tracker imports

Adding massive lists of trackers requires strict validation. The agent pulls the configuration templates using `get_indexer_schema`, maps your existing BigQuery tracker database to those templates, and pushes them via `add_indexer`. After the bulk import, the agent triggers `test_indexer` against every new entry. You can pipe those test results straight back into Vertex AI to build historical reliability models for your Usenet providers.

Automated tracker lifecycle management

Maintaining tracker health means knowing when to modify and when to purge. The agent reads specific configuration details via `get_indexer` to check for outdated domain names. If a domain is dead, the agent fires `update_indexer` with the new URL. If a tracker permanently shuts down, it executes `delete_indexer` to remove the dead weight, keeping your search queries fast and your Prowlarr database clean.

Setup guide

Set up Prowlarr (Indexers) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Prowlarr (Indexers) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Prowlarr (Indexers)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Prowlarr (Indexers) tools via MCP.",
    tools=mcp_tools,
)

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 Prowlarr. 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 Prowlarr (Indexers) 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 Prowlarr (Indexers) MCP in Google ADK

Install the `google-adk` package. Set up your `StreamableHttpServerParameters` with the endpoint, wrap it in an `McpToolset`, and assign it to your `LlmAgent` tools array.

You can filter the exposed tools using the `tool_names` parameter in the toolset configuration. This prevents your Gemini agent from accidentally calling destructive tools like `delete_indexer` while still allowing read access.

Gemini's massive context window lets you feed years of tracker downtime logs alongside current `get_indexer_status` results. It correlates historical outages with current failures to decide if an indexer is dead or just temporarily blocked.

You must use `get_indexer_schema`. Prowlarr refuses generic configurations. The agent fetches the exact JSON structure for that specific torrent site before pushing the final payload.

No. The MCP standard enforces strict isolation. The agent instructs the sandbox to run `test_indexer`, but your actual Usenet passwords and API tokens remain trapped inside the ephemeral Vinkius container.

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