Foundry MCP Usage Guide

A guide for using Foundry MCP, a project-management tool for AI coding assistants that stores structured project information in ~/.foundry/.

In plain words
What is it for?
It guides project documentation, specifications, context loading, workflow steps, and writing self-contained implementation instructions.
Why use it?
It explains how to give future developers or AI assistants enough context to continue a project without prior knowledge.

Cursor rule for Cursor

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 rules/cafreeman/foundry-mcp/foundry
Clone the repo
git clone --depth 1 https://github.com/cafreeman/foundry-mcp

Made for: Cursor.

Per session 5,368 This file is loaded in full into every session.
When invoked 5,368 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 $0.05368 $0.05368
Opus 5 $0.02684 $0.02684
Sonnet 5 $0.01074 $0.01074
Haiku 4.5 $0.00537 $0.00537

Measured 2d ago against content hash 52749713a47d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Foundry MCP Usage Guide 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 2d 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.

.cursor/rules/foundry.mdc · 530 lines

How it starts

The opening of the file, as written. The whole thing — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Foundry MCP Usage Guide for AI Assistants

Overview

Foundry MCP is a project management tool designed specifically for AI coding assistants. It provides structured project context, specification management, and workflow guidance through a standardized directory structure in ~/.foundry/.

Key Principles:

  • Content Agnostic: Foundry manages structure, not content opinions
  • LLM-Driven: You provide complete content as arguments
  • User-Controlled: Users control content, CLI manages structure
  • Workflow-Aware: Tools provide next-steps guidance for efficient development

CRITICAL: Understanding Document Purpose

These documents serve as COMPLETE CONTEXT for future LLMs and developers:

  • Each document must contain ALL information needed for someone with no prior project knowledge
  • Future LLMs will load these as PRIMARY reference for implementation work
  • Apply "Cold Start Test": Could a skilled developer implement using only this document?
  • Documents must be self-contained with comprehensive architectural and business context
  • Include implementation prerequisites, dependencies, decision rationale, and edge cases

Document Creation Mindset:

  • Write for someone who has never seen this project before
  • Include WHY decisions were made, not just WHAT was decided
  • Provide complete technical and business context for implementation
  • Assume the reader needs to understand the full system to implement successfully

Core Concepts

Project Structure

Each Foundry project contains:

  • vision.md: High-level product vision and goals (200+ characters, you provide)
  • tech-stack.md: Technology decisions and architecture (150+ characters, you provide)
  • summary.md: Concise context for quick LLM consumption (100+ characters, you provide)
  • specs/: Directory containing timestamped feature specifications

Specification Structure

Each spec contains:

  • spec.md: Detailed feature requirements, acceptance criteria, implementation approach
  • task-list.md: Implementation checklist with checkboxes (- [ ] task, - [x] completed)
  • notes.md: Additional context, design decisions, and implementation notes

Read the full file on GitHub · 530 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. 2d ago First seen · 530 lines · 5,368 tokens per session scan A 52749713a47d

Subscribe to this mod's changes

Foundry MCP Usage Guide is a cursor rule published in the GitHub repository cafreeman/foundry-mcp (4 stars, last pushed 5mo ago), licensed MIT. It adds 5,368 tokens to every session, about $0.0268 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.