podman-mcp AGENTS.md

podman-mcp AGENTS.md is an instructions file for Codex, OpenCode from sandraschi/podman-mcp. It costs 771 tokens per session, scanned A, original, MIT.

An AGENTS.md instruction file for a Podman MCP project, documenting its ports, technology stack, startup commands, tests, build commands, and tool structure.

In plain words
What is it for?
Use it when developing or testing the Podman MCP project, especially when adding tools or running its frontend, backend, tests, or native build.
Why use it?
It gives coding agents a quick reference for working in the project without having to rediscover its setup and conventions.

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sandraschi/podman-mcp/agents-md.svg)](https://agentmods.dev/instructions/sandraschi/podman-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sandraschi/podman-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/podman-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 771 This file is loaded in full into every session.
When invoked 771 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 $0.00771 $0.00771
Opus 5 $0.00385 $0.00385
Sonnet 5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured 4d ago against content hash 4dcee8a54bec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

podman-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

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

podman-mcp — AGENTS.md

Quick Reference

Ports Backend 11113 · Frontend 11112 · MCP /mcp
Stack FastMCP 3.5 · Python 3.12+ · uv · React 19 · Vite · Tailwind
Start .\web_sota\start.ps1
Tests uv run pytest
Lint npx tsc --noEmit (web_sota)
Build NSIS just build-native
CUA smoke just cua-nsis-test

Tool Pattern

All tools follow the portmanteau pattern — one function per domain with operation: Literal[...] discriminator. Tools auto-register via @mcp.tool() decorator on import.

Tool Module Operations
manage_containers tools/containers.py list, inspect, start, stop, restart, delete, create, logs, stats, exec, files, resources
manage_pods tools/pods.py list, inspect, create, start, stop, delete
manage_images tools/images.py list, inspect, pull, delete, build, search
manage_system tools/system.py status, info, machine_list/init/start/stop, prune, generate_systemd, volume_, network_
manage_compose tools/compose.py up, down, ps, logs, build, config, debug
manage_backup tools/backup.py save_image, load_image, export_container, import_container, save/load_volume, save_compose, list_backups
manage_migrate tools/migrate.py docker_compose_to_podman, podman_compose_to_docker, scan_docker_artifacts, migrate_image, compatibility_check, dockerfile_to_containerfile, export_for_docker
manage_agentic tools/agentic.py deploy_compose, cleanup, diagnose, rollback, health_sweep
manage_health tools/health.py container_analyze, system_overview, recommendations

Key Files

File Purpose
src/server.py FastAPI app + CORS + lifespan + web UI mount
src/podmanmcp/mcp_instance.py FastMCP singleton, tool registration trigger
src/podmanmcp/tool_registration.py Imports all tool modules (decorators fire on import)
src/podmanmcp/podman_context.py Podman CLI resolution (native/WSL2), run_podman_command(), check_podman_available decorator
src/podman_mcp/web.py All REST endpoints: dashboard, health, chat, diagnostics, compose REST bridge
web_sota/src/App.tsx React router (13 routes)
web_sota/src/lib/api.ts API_BASE constant
web_sota/src/store/connection.ts Zustand store for backend connection state

Read the full file on GitHub · 49 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 · 49 lines · 771 tokens per session scan A 4dcee8a54bec

Subscribe to this mod's changes

podman-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/podman-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 771 tokens to every session, about $0.0039 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.