steam-mcp AGENTS.md

steam-mcp AGENTS.md is an instructions file for Codex, OpenCode from sandraschi/steam-mcp. It costs 598 tokens per session, scanned A, original, MIT.

A repository instruction file for Steam-MCP, a server that lets software access Steam profiles, game libraries, statistics, store information, and Workshop items. Steam is a platform for buying and playing PC games.

In plain words
What is it for?
Developing or operating Steam profile, library, statistics, store, Workshop, system-status, and chat features.
Why use it?
It documents the available services, ports, login settings, AI chat options, and commands so an agent can work with the project correctly.

Instructions file for CodexOpenCode

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/sandraschi/steam-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/sandraschi/steam-mcp

Made for: Codex, OpenCode.

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 steam-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sandraschi/steam-mcp/agents-md.svg)](https://agentmods.dev/instructions/sandraschi/steam-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sandraschi/steam-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/steam-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 598 This file is loaded in full into every session.
When invoked 598 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 $0.00598 $0.00598
Opus 5 $0.00299 $0.00299
Sonnet 5 $0.00120 $0.00120
Haiku 4.5 $0.00060 $0.00060

Measured 4d ago against content hash b37e3e131ef5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

steam-mcp AGENTS.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.

AGENTS.md · 49 lines

What it actually says

Steam-MCP Agent Context

Repo

steam-mcp — FastMCP 3.2 portmanteau server for Steam profile, library, stats, store, and Workshop. v0.3.1

Ports

  • Backend: 11020 (FastAPI + MCP HTTP at /mcp)
  • Frontend: 11021 (Vite dev; Tauri native uses same webapp)
  • Env: BACKEND_PORT, FRONTEND_PORT

Auth

  • STEAM_API_KEY — profile, library, workshop, wishlist
  • STEAM_ID — default account for own profile / library
  • Public: store search, app details, news, player counts

AI / chat (webapp)

  • STEAM_CHAT_MODEhybrid (default) | llm | rules
  • AI_PROVIDER, AI_ENDPOINT, AI_MODEL — Ollama / OpenAI-compatible
  • STEAM_SAMPLING_BASE_URL — fallback for AI_ENDPOINT
  • STEAM_PREFAB_APPS=0 — disable prefab-ui App tools (dict fallbacks)

Portmanteau tools

  • steam_profile — own | summaries | friends | resolve_vanity
  • steam_library — owned | recent | details | wishlist
  • steam_stats — achievements | global_percentages | players | leaderboards
  • steam_store — news | search | reviews
  • steam_workshop — query | item_details
  • steam_system — status | steamcmd_status
  • steam_help, agentic_steam_workflow, Prefab show_* cards

Packaging

  • manifest.json + just mcpb-packdist/steam-mcp.mcpb
  • glama.json, llms.txt, llms-full.txt — discovery / LLM corpus
  • native/ — Tauri 2 + PyInstaller sidecar (build-sidecar.ps1, build.ps1)

Layout

  • src/steam_mcp/services/ — Steam API logic
  • src/steam_mcp/mcp/tools/ — portmanteau, prefab, prompts, resources, agentic
  • src/steam_mcp/skills/steam-mcp/SKILL.md — agent skill (also SkillsDirectoryProvider)

Commands

  • just run — STDIO MCP
  • just serve — HTTP + REST + MCP
  • just test / just smoke / just mcpb-pack
  • just native-dev / just native-build
  • start.ps1 / webapp/start.ps1 — full stack

Install docs: mcp-central-docs/standards/AGENT_INSTALL_REFERENCE.md

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 · 49 lines · 598 tokens per session scan A b37e3e131ef5

Subscribe to this mod's changes

steam-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/steam-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 598 tokens to every session, about $0.0030 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.