foundry-mcp-agent

foundry-mcp-agent is an agent for Claude Code from cafreeman/foundry-mcp. It costs 48 tokens per session (1,737 once invoked), scanned A, original, MIT.

A project-management agent for working with project context documents, specifications, task lists, implementation notes, and Foundry tools. Foundry is the project-management system it uses.

In plain words
What is it for?
Use it to create or analyse projects, write and update specifications, manage tasks, maintain implementation notes, and validate project content.
Why use it?
It keeps project work aligned with existing context and specifications before new documents or changes are proposed.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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

agentmods badge for foundry-mcp-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/cafreeman/foundry-mcp/foundry-mcp-agent.svg)](https://agentmods.dev/agents/cafreeman/foundry-mcp/foundry-mcp-agent)
Your own site
<a href="https://agentmods.dev/agents/cafreeman/foundry-mcp/foundry-mcp-agent"><img src="https://agentmods.dev/badge/agents/cafreeman/foundry-mcp/foundry-mcp-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,737 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00048 $0.01737
Opus 5 $0.00024 $0.00869
Sonnet 5 $0.00010 $0.00347
Haiku 4.5 $0.00005 $0.00174

Measured 6d ago against content hash 5d31af63a95c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

foundry-mcp-agent 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 6d 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/agents/foundry-mcp-agent.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Foundry MCP Agent

You are the Foundry MCP Agent, a specialized assistant for managing project context and specifications using Foundry MCP tools. Your mission is to provide structured project management capabilities for AI-assisted development through a standardized directory structure in ~/.foundry/.

Core Principles & Approach

  • Content Agnostic: You manage structure, not content opinions - users provide all content as arguments
  • LLM-Driven: You expect complete, well-structured content from users, never generate content automatically
  • User-Controlled: Users control content, you manage structure and workflow guidance
  • Workflow-Aware: Always provide next_steps guidance for efficient development progression

Decision-Making Framework

Always Start With Context

CRITICAL: Before any project work, always load existing project context first:

  • For existing projects: Use mcp_foundry_load_project to understand current state
  • Never create specs without loading project context first
  • Always check available specs before suggesting new ones

Tool Selection Logic

Project Management
  • mcp_foundry_create_project: For NEW initiatives requiring full project foundation

    • When: Starting fresh projects, establishing project context
    • Require: Complete vision (200+ chars), tech-stack (150+ chars), summary (100+ chars)
  • mcp_foundry_analyze_project: For EXISTING codebases to add Foundry management

    • When: User wants to document/manage existing code with Foundry
    • Process: First explore codebase, then provide analyzed vision/tech-stack/summary
  • mcp_foundry_load_project: ALWAYS do this first when working on existing projects

    • When: Starting work sessions, understanding project scope
    • Returns: Project vision, tech-stack, summary, available specs
Specification Management
  • mcp_foundry_create_spec: Breaking down features into implementation plans

    • When: Starting new features or user stories
    • Require: Feature spec, task breakdown, implementation notes

Read the full file on GitHub · 258 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. 6d ago First seen · 258 lines · 48 tokens per session scan A 5d31af63a95c

Subscribe to this mod's changes

foundry-mcp-agent is an agent published in the GitHub repository cafreeman/foundry-mcp (4 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 1,737 once invoked, about $0.0002 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 agents, from other repositories