How to Use the Prowlarr (Indexers) MCP in AutoGen

Q: Do I need to write custom tool-handling code for AutoGen?

No. The autogen-extmcp package provides an adapter that automatically converts the MCP Server tools into a format that AutoGen agents can use directly. You just pass the tools list to your agent's constructor.

Let a team of AutoGen agents debate and manage your Prowlarr indexer health.

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 AutoGen

Create your Vinkius account to connect Prowlarr (Indexers) to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Set Up an Agent Debate on Indexer Health

This is where AutoGen shines. Create a `MonitorAgent` that uses `get_indexer_status` to flag a problem. It then reports to a `MaintenanceAgent` that wants to immediately `delete_indexer`. A third `QualityAgent` can step in, arguing that deletion is too destructive. It suggests using `update_indexer` to simply disable it first, then re-running `test_indexer` after an hour. The agents debate and reach a consensus before acting.

Build a Secure Configuration Agent

Task a team of agents with adding a new indexer. A `PlannerAgent` gets the requirements from the user. It asks a `ToolAgent` to call `get_indexer_schema` to find the correct fields. Before the `ToolAgent` calls `add_indexer` with the new API key, a `SecurityAgent` can review the plan, ensuring no sensitive data is logged and that the indexer protocol is correct. This multi-agent review process catches errors before they happen.

Your AutoGen MCP Server for Indexer Management

The Prowlarr tools are exposed to your entire group of AutoGen agents. Any agent in the conversation can be granted the ability to call `list_indexers`, `get_indexer`, or any other tool. This allows you to build complex, conversational workflows. You can simply tell the agent group, "One of my indexers is slow, figure out which one and fix it," and they'll use the available tools to investigate and resolve the issue together.

Setup guide

Set up Prowlarr (Indexers) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Prowlarr (Indexers) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Prowlarr (Indexers)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Prowlarr (Indexers) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Prowlarr (Indexers)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Prowlarr (Indexers) data")
    print(result.messages[-1].content)

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 AutoGen

Define different agents with distinct roles, like a 'monitor' and a 'technician'. Give them access to the Prowlarr tools, a shared goal, and let them converse to decide on actions like using `test_indexer` or `update_indexer`.

Yes, this is a perfect use case for AutoGen. One agent can propose deleting an indexer with `delete_indexer`, while another can argue for a less drastic approach like disabling it via `update_indexer`. They will debate until they reach an agreed-upon solution.

A user proxy agent could ask a manager agent to "check the health of all my indexers." The manager then directs a worker agent to call `list_indexers` and `get_indexer_status`, reporting the findings back to the group for the next step.

No. The `autogen-ext[mcp]` package provides an adapter that automatically converts the MCP Server tools into a format that AutoGen agents can use directly. You just pass the tools list to your agent's constructor.

Sensitive indexer data like API keys never leaves your self-hosted Prowlarr. When your AutoGen agents use these tools, they send commands through a secure Vinkius endpoint. The MCP server itself is stateless and ephemeral, meaning it holds no data after your request is complete.

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