What is prowlarr-mcp AGENTS.md?

Developer instructions for an MCP server that exposes Prowlarr’s REST API, a web interface for programs. Prowlarr manages indexers, applications, download clients, proxies, notifications, tags, filters, searches, and system commands.

Guiding development, offline tests, live integration tests, write-enabled tests, version bumps, and safe handling of Prowlarr read and write operations.

They document how to test and release the server while making clear that many Prowlarr operations can change or delete data.

How arr-mcps/prowlarr-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to arr-mcps/prowlarr-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/arr-mcps/prowlarr-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/arr-mcps/prowlarr-mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/arr-mcps/prowlarr-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/arr-mcps/prowlarr-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/arr-mcps/prowlarr-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/arr-mcps/prowlarr-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/arr-mcps/prowlarr-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/arr-mcps/prowlarr-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,257 This file is loaded in full into every session.

When invoked 1,257 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01257	$0.01257
Opus 5.5	$0.00503	$0.00503
Sonnet 5.5	$0.00251	$0.00251
Haiku 4.5	$0.00126	$0.00126

Measured 2mo ago against content hash d58c8cfcb22b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prowlarr-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — prowlarr-mcp

MCP server exposing Prowlarr's API v1 (REST) as tools so an LLM can manage indexers, applications, download clients, indexer proxies, notifications, tags, and custom filters, plus run cross-indexer searches and issue system commands. Unlike tracearr-mcp, Prowlarr has a full read/write surface — many operations create, update, delete, or trigger actions. Uses FastMCP, uv for deps.

Exposed as 10 resource-scoped portmanteau tools, not one tool per operation — see "Portmanteau registration" below. A prior version registered all 116 operations individually; that blew the MCP context budget (~116 tools × ~250 tokens ≈ 29k tokens just for this one server) and has been retired.

Testing

Offline suite: make test (or uv run pytest)
Live integration (needs PROWLARR_URL/PROWLARR_API_KEY): make test-integration
Write integration (scratch Tag round-trip) additionally needs PROWLARR_ALLOW_WRITES=1 so plain make test-integration never mutates the instance.

Release workflow

Always use the make bump-* targets to bump the version (uv version --bump patch|minor|major), which updates pyproject.toml and uv.lock together. Do NOT edit the version by hand.

Bump: make bump-patch (or bump-minor / bump-major)
Commit message is just the version, e.g. 0.1.2 — nothing else.
Tag it v<version> (e.g. v0.1.2).

Push main and the tag:

git push origin main
git push origin v<version>

Deploy to the Proxmox host (root SSH key): pull the repo then reinstall the uv tool:
```
ssh [email protected] -- 'cd /root/prowlarr-mcp && git fetch origin && git reset --hard origin/main'
ssh [email protected] -- 'cd /root/prowlarr-mcp && uv tool install --force .'
```
The host runs it via uv tool install → /root/.local/bin/prowlarr-mcp (not from the repo). There is no /home/savagecore/Documents/christopfarr/mcp/prowlarr-mcp copy.

Read/write notes

The Prowlarr API is not read-only: most operations are NOT read-only. Conventions:

GET operations: originally readOnlyHint=True at the individual-function level.
DELETE operations and /system/shutdown + /system/restart: originally destructiveHint=True.
POST/PUT operations (create/update/test/action/command): originally no hints (state-changing but non-destructive).
Auth is the X-Api-Key header. build_client targets the server root; _req prefixes /api/v1 to relative paths, and /api + /ping are used verbatim. Keep the whole server in prowlarr_mcp.py unless it outgrows it.

Read the full file on GitHub · 53 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 53 lines · 1,257 tokens per session scan A d58c8cfcb22b

Subscribe to this mod's changes

prowlarr-mcp AGENTS.md is an instructions file published in the GitHub repository arr-mcps/prowlarr-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 1,257 tokens to every session, about $0.0050 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

prowlarr-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
prowlarr-mcp AGENTS.mdarr-mcps/prowlarr-mcp	Instructions file	0	2d ago	MIT	A	1,257	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

prowlarr-mcp: Instructions file for Codex