What is elgato-mcp-server CLAUDE.md?

A repository guide for developing an MCP server that connects AI assistants to Elgato applications such as Stream Deck through local app communication.

Use it when building, formatting, testing, or understanding this TypeScript MCP server, including its standard and integration tests.

It gives contributors the project’s commands, architecture, and development workflow so they can make changes without guessing how the bridge works.

How elgatosf/elgato-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to elgatosf/elgato-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/elgatosf/elgato-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/elgatosf/elgato-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/elgatosf/elgato-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/elgatosf/elgato-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/elgatosf/elgato-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/elgatosf/elgato-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.

Your own site · 80×15

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

Per session 962 This file is loaded in full into every session.

When invoked 962 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	$0.00962	$0.00962
Opus 5	$0.00481	$0.00481
Sonnet 5	$0.00192	$0.00192
Haiku 4.5	$0.00096	$0.00096

Measured 10d ago against content hash df7d5bf2c3f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

elgato-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 10d 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 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 (claude.ai/code) when working with code in this repository.

Project Overview

MCP server bridging AI assistants (Claude Desktop) and Elgato apps (e.g., Stream Deck) via the Model Context Protocol. The bridge discovers tools/resources from connected apps over IPC and exposes them to MCP clients through stdio or HTTP transports.

Commands

pnpm build              # Compile TypeScript (outputs to bin/)
pnpm lint               # ESLint with zero warnings tolerance
pnpm lint:fix           # Prettier formatting
pnpm test               # All tests (Vitest)
pnpm test:unit          # Unit tests only
pnpm test:integration   # Integration tests only
pnpm test:coverage      # Tests with coverage report
pnpm test:watch         # Watch mode

Run a single test file:

pnx vitest run src/__tests__/unit/McpBridge.test.ts

Run a single test by name:

pnx vitest run -t "test name pattern"

Architecture

Data flow: MCP Client → Transport (stdio/HTTP) → McpBridge → ClientManager → IpcClient → App IPC socket

Four core components:

IpcClient (src/IpcClient.ts) — Generic IPC socket client for communicating with a single app. Manages connection lifecycle with dual reconnection strategy (signal socket + polling fallback). Handles request/response correlation with timeouts. Platform-aware: Unix sockets on macOS/Linux, named pipes on Windows.
ClientManager (src/ClientManager.ts) — Manages multiple IpcClient instances (one per known app). Aggregates tools and resources with appname__ prefixes and routes tool calls to the correct client. Forwards connection events and notifications.
McpBridge (src/McpBridge.ts) — Protocol bridge creating the MCP server with tool/resource handlers. Delegates to ClientManager for tool/resource operations, manages change notifications, and forwards elicitation requests. Two factory functions: createInitializedBridge() for HTTP (manual transport attachment) and createConnectedBridge(transport) for stdio (single transport).

Read the full file on GitHub · 75 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.

10d ago First seen · 75 lines · 962 tokens per session scan A df7d5bf2c3f8

Subscribe to this mod's changes

elgato-mcp-server CLAUDE.md is an instructions file published in the GitHub repository elgatosf/elgato-mcp-server (10 stars, last pushed 6d ago), licensed MIT. It adds 962 tokens to every session, about $0.0048 per session on Opus 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.

Building agents

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

elgato-mcp-server: Instructions file for Claude Code