What is plex-mcp CLAUDE.md?

A project instruction file for plex-mcp, a Docker-based server that lets software communicate with Plex Media Server through the MCP standard. It describes the TypeScript stack, project status source, and code layout.

Use it when changing the MCP server, its HTTP route, Plex API integration, environment handling, Docker setup, or related tests.

It helps coding agents follow the project’s runtime, security, testing, and file-organization rules instead of guessing how the server works. It also identifies where current work is recorded.

How CarlDog/plex-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to CarlDog/plex-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/plex-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/CarlDog/plex-mcp

Made for: Claude Code.

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/plex-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/carldog/plex-mcp/claude-md)

Your own site

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

Per session 2,451 This file is loaded in full into every session.

When invoked 2,451 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 86% copy Near-identical to another mod 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	$0.02451	$0.02451
Opus 5.5	$0.00980	$0.00980
Sonnet 5.5	$0.00490	$0.00490
Haiku 4.5	$0.00245	$0.00245

Measured 2mo ago against content hash 036e2e54859f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plex-mcp CLAUDE.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

This is a copy

86% identical to plex-mcp AGENTS.md — 51 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

plex-mcp

MCP server for Plex Media Server, packaged as a Docker container.

Fleet standards: ts-mcp-server v1.0 — audited 2026-07-25

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
Plex HTTP API via fetch (no Plex SDK dependency)
Docker multi-stage build (alpine, non-root)

Layout

src/index.ts — MCP server entry. Decides transport based on MCP_PORT.
src/mcp-route.ts — the Streamable HTTP /mcp route: Host/Origin allowlist, optional bearer auth, per-session transport map, idle sweep, session dispatch. Split out of index.ts so it can be imported by a test — index.ts self-executes on import, so nothing in it was reachable without booting a server. Covered by tests/mcp-route.test.ts.
src/shared/mcp-environment.ts — fleet-canonical Host/Origin matching and env-parsing helpers, copied verbatim from the same module live in kindroid-mcp/servarr-mcp/filesystem-mcp/portainer-mcp/mnemosyne-mcp/ watch-companion/downloader-mcp. src/mcp-route.ts uses only requestAuthorityAllowed (host-only, via an omitted origin key); src/config.ts uses parseAllowedHosts for strict per-entry validation. Covered by tests/mcp-environment.test.ts.
src/plex.ts — Plex HTTP API client.
src/tautulli.ts — optional direct Tautulli HTTP client, fail-soft config, normalized privacy-allowlisted response types.
src/log.ts — small structured logger (stderr, level-gated via LOG_LEVEL env var). See README for format and levels.
src/tools/ — tool registrations split per domain (discovery.ts, sessions.ts, playback.ts, playlists.ts, hubs.ts, admin.ts, images.ts, diagnostics.ts, tautulli.ts). index.ts orchestrates via registerTools(server, plex, tautulli); helpers.ts holds shared utilities (asText, withLogging).
Dockerfile — multi-stage build for the runtime image.
docker-compose.yml — Compose/Portainer deployment using HTTP transport.
docs/PLEX-API.md — curated reference for the Plex HTTP API: external doc links, gotchas we've hit (pagination pairing, /:/scrobble empty responses, type integer codes), and rough endpoint shapes for capabilities we haven't built yet. Read this before adding new tools.
docs/CHATGPT-APPS-SDK.md — future-work spec for making plex-mcp consumable from a ChatGPT account (OAuth 2.1 protected-resource setup, tool annotation hints, optional UI widgets, infrastructure choices). Not started; phased plan inside.
.githooks/pre-commit — gitleaks + PII pattern scan.
.gitleaks.toml — secret-scanning config.

Read the full file on GitHub · 196 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 Changed 036e2e54859f
2mo ago First seen · 196 lines · 2,451 tokens per session scan A 73c4c924a1c7

Subscribe to this mod's changes

plex-mcp CLAUDE.md is an instructions file published in the GitHub repository CarlDog/plex-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 2,451 tokens to every session, about $0.0098 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to plex-mcp AGENTS.md, differing in 51 lines, and is treated as a copy.

plex-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
plex-mcp CLAUDE.mdCarlDog/plex-mcp	Instructions file	1	4d ago	MIT	A	2,451	Claude Code
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

plex-mcp: Instructions file for Claude Code