What is foundryvtt-mcp CLAUDE.md?

A project guide for an MCP server that connects AI assistants to FoundryVTT, software for running tabletop role-playing games online. It documents the codebase, tools, commands, architecture, and data flow.

Use it when building, testing, formatting, linting, or tracing requests through the foundryvtt-mcp TypeScript project.

It gives the coding agent project-specific guidance instead of making assumptions about the technology or how the code is organised.

How RN0000/foundryvtt-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to RN0000/foundryvtt-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/RN0000/foundryvtt-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/RN0000/foundryvtt-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/rn0000/foundryvtt-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/rn0000/foundryvtt-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/rn0000/foundryvtt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rn0000/foundryvtt-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/rn0000/foundryvtt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rn0000/foundryvtt-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 936 This file is loaded in full into every session.

When invoked 936 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 100% 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	$0.00936	$0.00936
Opus 5.5	$0.00374	$0.00374
Sonnet 5.5	$0.00187	$0.00187
Haiku 4.5	$0.00094	$0.00094

Measured 2mo ago against content hash af24705b9e11, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

foundryvtt-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

100% identical to foundryvtt-mcp CLAUDE.md — 0 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 · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project: foundryvtt-mcp

Model Context Protocol (MCP) server bridging AI assistants with FoundryVTT tabletop gaming software.

Tech Stack

Language: TypeScript (ES modules, .js imports for MCP SDK compatibility)
Runtime: Node.js (Bun as package manager)
Test: Vitest (unit + integration), Playwright (E2E)
Lint/Format: Biome (linting + formatting)
Validation: Zod schemas

Essential Commands

bun run build          # Compile TypeScript
bun run dev            # Development mode with hot reload
bun test               # Unit tests (Vitest)
bun run test:integration # Integration tests (needs :30001 container + .env.integration — prefer `just test-integration-docker`)
bun run test:e2e       # E2E tests (Playwright, headless)
bun run lint           # Lint code (Biome)
bun run lint:fix       # Auto-fix lint issues
bun run format         # Format code (Biome)
bun run test-connection # Test MCP→FoundryVTT connection

Architecture

Data Flow

AI assistant calls MCP tool → src/tools/router.ts
Router dispatches to handler → src/tools/handlers/
Handler queries cached worldData → src/foundry/client.ts
Response returned as MCP result

Key Modules

Module	Path	Purpose
Client	`src/foundry/client.ts`	Socket.IO connection, world state cache
Auth	`src/foundry/auth.ts`	4-step Socket.IO authentication
Config	`src/config/index.ts`	Zod-validated environment config
Tools	`src/tools/definitions.ts`	MCP tool schemas
Router	`src/tools/router.ts`	Request→handler dispatch
Types	`src/foundry/types.ts`	FoundryVTT entity interfaces

Authentication & transport selection

client.ts selects transport purely by whether FOUNDRY_API_KEY is set:

FOUNDRY_API_KEY unset → Socket.IO mode (default): authenticates with FOUNDRY_USERNAME/FOUNDRY_PASSWORD and loads full worldData.
FOUNDRY_API_KEY set → REST API mode: connects to the REST module's /api/status instead. This is a transport switch, not an additive layer — it does not run alongside the Socket.IO worldData path.
USE_REST_MODULE (seen in some .env/example files and the test-connection tips) is not read by src/config/index.ts — it is a no-op. Transport is decided solely by apiKey presence.

Read the full file on GitHub · 86 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 · 86 lines · 936 tokens per session scan A af24705b9e11

Subscribe to this mod's changes

foundryvtt-mcp CLAUDE.md is an instructions file published in the GitHub repository RN0000/foundryvtt-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 936 tokens to every session, about $0.0037 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to foundryvtt-mcp CLAUDE.md, differing in 0 lines, and is treated as a copy.

foundryvtt-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
foundryvtt-mcp CLAUDE.mdRN0000/foundryvtt-mcp	Instructions file	0	1mo ago	MIT	A	936	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

foundryvtt-mcp: Instructions file for Claude Code