What is servarr-mcp AGENTS.md?

A project instruction file for servarr-mcp, a Docker-based MCP server for Sonarr, Radarr, Lidarr, Readarr, and Prowlarr. These are self-hosted apps for managing media libraries and downloads.

Use it when maintaining integrations with the Servarr apps, including status, queue, history, authentication, and container builds.

It points the agent to the project’s current status and defines the code structure, APIs, runtime, and deployment rules.

How CarlDog/servarr-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to CarlDog/servarr-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/CarlDog/servarr-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/CarlDog/servarr-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/carldog/servarr-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/carldog/servarr-mcp/agents-md)

Your own site

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

Per session 2,460 This file is loaded in full into every session.

When invoked 2,460 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	$0.02460	$0.02460
Opus 5.5	$0.00984	$0.00984
Sonnet 5.5	$0.00492	$0.00492
Haiku 4.5	$0.00246	$0.00246

Measured 2mo ago against content hash 5024b59bed03, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

servarr-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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

servarr-mcp CLAUDE.md — 91% identical, 30 lines differ

AGENTS.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

servarr-mcp

MCP server for the Servarr stack (Sonarr, Radarr, Lidarr, Readarr, Prowlarr), packaged as a Docker container.

Status

Single source of truth: STATUS.md. Do not duplicate status into this file, MEMORY.md, or Serena memories — reference STATUS.md.

Current Sprint

See STATUS.md for the active phase, what's done, and what's next.

Stack

TypeScript (Node 22+, ESM, NodeNext module resolution)
@modelcontextprotocol/sdk (high-level McpServer API)
zod for tool input schemas
Servarr REST APIs accessed directly via fetch (no third-party client)
Docker multi-stage build (alpine, non-root user)

Layout

src/index.ts — MCP server entry / composition root. Computes which apps are enabled from env vars at startup, then decides transport (stdio vs HTTP) based on MCP_PORT. Per-session McpServer instances via the createServer() factory; client instances are computed once at startup.
src/clients/base.ts — ServarrClient base class with shared HTTP plumbing (X-Api-Key auth, request helper, common endpoints: systemStatus, queue, history). Also exports the asText() helper.
src/clients/<app>.ts — one file per app, holding only the <App>Client class (subclass of ServarrClient with app-specific resource methods). Today: sonarr.ts, radarr.ts, lidarr.ts, readarr.ts, prowlarr.ts.
src/tools/<app>/index.ts — MCP tool registrations for that app. Each exports a register<App>Tools(server, client) function. Today each app's index.ts holds all of that app's registrations directly. As tool counts grow, pull resource groups into sibling files (series.ts, wanted.ts, etc.) — see "Per-resource splitting" below.
docs/SERVARR-API.md — cross-cutting Servarr API reference (auth, paging, command pattern, errors).
docs/<app>.md — per-app endpoint catalogue + tool decisions (current tools, candidate read/write tools, out-of-scope, gotchas).
docs/specs/<app>.json — version-pinned OpenAPI spec snapshots.
Dockerfile — multi-stage build (alpine, non-root)
docker-compose.yml — Compose/Portainer deployment using HTTP transport
.githooks/pre-commit — gitleaks + PII pattern scan

Read the full file on GitHub · 217 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 · 217 lines · 2,460 tokens per session scan A 5024b59bed03

Subscribe to this mod's changes

servarr-mcp AGENTS.md is an instructions file published in the GitHub repository CarlDog/servarr-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 2,460 tokens to every session, about $0.0098 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.

servarr-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
servarr-mcp AGENTS.mdCarlDog/servarr-mcp	Instructions file	1	3d ago	MIT	A	2,460	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

servarr-mcp: Instructions file for Codex