plex-mcp-server: Instructions file for Claude Code

CLAUDE.md

plex-mcp-server CLAUDE.md is an instructions file for Claude Code from x10send/plex-mcp-server. It costs 1,065 tokens per session, scanned A, original, MIT.

Repository instructions for developing and testing x10send/plex-mcp-server, an MCP server that connects clients to Plex over HTTP.

In plain words
What is it for?
Use them to install dependencies, run the server with hot reload, run tests or one test file, check coverage, type-check, format, build, and create a Docker image.
Why use it?
They provide the exact dependency, development, testing, checking, and build commands expected by the project.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is x10send/plex-mcp-server's own configuration. It tells Claude Code how to work on plex-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything plex-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to x10send/plex-mcp-server. 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/x10send/plex-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/x10send/plex-mcp-server

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.

agentmods badge for plex-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/x10send/plex-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/x10send/plex-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/x10send/plex-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/x10send/plex-mcp-server/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.

agentmods 80×15 button for plex-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/x10send/plex-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/x10send/plex-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,065 This file is loaded in full into every session.
When invoked 1,065 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01065 $0.01065
Opus 5.5 $0.00426 $0.00426
Sonnet 5.5 $0.00213 $0.00213
Haiku 4.5 $0.00106 $0.00106

Measured 2mo ago against content hash 0c831bfcda19, 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-server 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.

CLAUDE.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code when working with this repository.

Commands

# Install dependencies
npm ci

# Start dev server (hot reload)
npm run dev

# Run all quality checks (format → lint → typecheck → test+coverage → build)
npm run check

# Run tests only
npm test

# Run a single test file
node --import tsx --test test/library.test.ts

# Run tests with coverage (enforces thresholds)
npm run test:coverage

# Type-check without emitting
npm run typecheck

# Format source
npm run format

# Build to dist/
npm run build

# Build Docker image locally
docker build -t plex-mcp-server .

# Run locally (direct token mode)
docker run --rm \
  -e PLEX_URL=http://192.168.1.x:32400 \
  -e PLEX_TOKEN=your-token \
  -p 3003:3000 \
  plex-mcp-server

The npm run check pipeline is the gate: format check → lint → typecheck → test+coverage → build. CI runs the same command.

Architecture

Stateless Fastify HTTP server exposing MCP Streamable HTTP at POST/GET/DELETE /mcp. Each request creates a fresh McpServer + StreamableHTTPServerTransport pair (stateless mode, sessionIdGenerator: undefined).

Token resolution per request: X-Plex-Token header (injected by mcp-edge-gateway) → PLEX_TOKEN env var → 401. The token is never logged.

Module responsibilities:

  • src/server.ts — entry point only: loads config, calls buildApp, binds socket, SIGTERM/SIGINT. Excluded from coverage.
  • src/app.ts — Fastify app: health endpoint, MCP route, token resolution, per-request McpServer + transport lifecycle.
  • src/config.ts — env loading, PLEX_URL SSRF validation (blocks public IPs at startup), log level and port validation.
  • src/plex-client.ts — typed Plex HTTP API client. Exports IPlexClient interface (used for test mocking) and PlexClient implementation. PlexApiError for non-2xx responses.
  • src/tools/library.ts — exports registerLibraryTools(server, client). Tools: get_libraries, get_library_contents, get_children, get_media_info, get_media_extras.
  • src/tools/discovery.ts — exports registerDiscoveryTools(server, client). Tools: search_media, get_genres, get_actors, get_directors, get_collections, get_collection_items, get_related, get_recently_added, get_on_deck, get_watch_history, get_random_items.

Read the full file on GitHub · 93 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.

  1. 2mo ago First seen · 93 lines · 1,065 tokens per session scan A 0c831bfcda19

Subscribe to this mod's changes

plex-mcp-server CLAUDE.md is an instructions file published in the GitHub repository x10send/plex-mcp-server (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,065 tokens to every session, about $0.0043 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.

Related

plex-mcp-server CLAUDE.md compared with instructions from other repositories

plex-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
plex-mcp-server CLAUDE.mdx10send/plex-mcp-serverInstructions file12mo agoMITA1,065Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode