mcp-server-if CLAUDE.md

mcp-server-if CLAUDE.md is an instructions file for coding agents from davidar/mcp-server-if. It costs 3,059 tokens per session, scanned A, original, MIT.

A repository guide for Claude Code, the coding assistant used in this project. It explains the project, setup commands, tests, code checks, and package build process for an MCP server that lets AI assistants play text adventure games.

In plain words
What is it for?
Use it when working on this repository, especially to install dependencies, compile its game interpreters, run all tests or one test, lint and format code, check types, or build the package.
Why use it?
It gives the assistant the project context and exact commands needed to work consistently. It reduces guesswork when setting up the project, running tests, checking code, or building it.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/davidar/mcp-server-if/claude-md
Clone the repo
git clone --depth 1 https://github.com/davidar/mcp-server-if

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 mcp-server-if CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/davidar/mcp-server-if/claude-md.svg)](https://agentmods.dev/instructions/davidar/mcp-server-if/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/davidar/mcp-server-if/claude-md"><img src="https://agentmods.dev/badge/instructions/davidar/mcp-server-if/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,059 This file is loaded in full into every session.
When invoked 3,059 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03059 $0.03059
Opus 5 $0.01529 $0.01529
Sonnet 5 $0.00612 $0.00612
Haiku 4.5 $0.00306 $0.00306

Measured 4d ago against content hash da48f3fe425c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-server-if 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 4d 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 · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 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 for playing interactive fiction games (Glulx and Z-machine). Enables AI assistants to play text adventure games (.ulx, .gblorb, .z3-.z8, .zblorb) via the Model Context Protocol. Uses compiled interpreters (glulxe for Glulx, bocfel for Z-code) with RemGlk as subprocesses, communicating via JSON (RemGlk protocol).

Common Commands

# Setup (clones submodules, installs deps, AND compiles glulxe+bocfel binaries)
# Requires both a C compiler (cc/gcc) and C++ compiler (c++/g++/clang++)
uv sync --group dev --reinstall-package mcp-server-if

# Run all unit tests
uv run pytest -v

# Run a single test file
uv run pytest tests/test_session.py -v

# Run a single test by name
uv run pytest -k "test_play_if_basic" -v

# Integration tests (require compiled glulxe + network)
uv run pytest -m integration -v

# Lint and format
uv run ruff check src/ tests/
uv run ruff format src/ tests/

# Type check
uv run pyright src/

# Build package (compiles glulxe from C source via hatch_build.py)
uv build

Important: uv sync compiles glulxe and bocfel into src/mcp_server_if/bin/ via the hatch build hook (editable install). The build hook skips compilation if binaries already exist; use --reinstall-package mcp-server-if to force recompilation. Bocfel requires a C++ compiler (g++/c++/clang++).

Architecture

MCP Server (FastMCP)
    └── server.py      — 6 MCP tools + journal management + interpreter routing
        └── session.py — GlulxSession: async subprocess ↔ RemGlk JSON protocol
            ├── glulxe binary (Glulx games, compiled from deps/glulxe + deps/remglk)
            └── bocfel binary (Z-code games, compiled from deps/garglk/terps/bocfel + deps/remglk)

config.py — Resolves paths (env vars → bundled binary → PATH) and validates config

Data flow per turn: server.play_if() → detects game format → selects interpreter (glulxe or bocfel) → GlulxSession.run_turn(command) → spawns interpreter subprocess → sends JSON input (RemGlk format) → reads JSON output → formats to Markdown text.

Read the full file on GitHub · 160 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. 4d ago First seen · 160 lines · 3,059 tokens per session scan A da48f3fe425c

Subscribe to this mod's changes

mcp-server-if CLAUDE.md is an instructions file published in the GitHub repository davidar/mcp-server-if (0 stars, last pushed 7mo ago), licensed MIT. It adds 3,059 tokens to every session, about $0.0153 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.

Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,733 tokens