What is podman-mcp-server AGENTS.md?

A project guide for a Go server that lets AI assistants manage Podman or Docker containers through MCP. It describes the agent interface, repository layout, configuration, tool definitions, and container-runtime abstraction.

It helps developers add MCP tools and agent implementations, configure the server, and work with containers, images, networks, and volumes through the project's Go packages.

It gives contributors the conventions needed to extend the server without bypassing its existing interfaces. This reduces confusion about where new tools and runtime behavior belong.

How manusa/podman-mcp-server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to manusa/podman-mcp-server. 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/manusa/podman-mcp-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/manusa/podman-mcp-server

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/manusa/podman-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/manusa/podman-mcp-server/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/manusa/podman-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/manusa/podman-mcp-server/agents-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/manusa/podman-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/manusa/podman-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,778 This file is loaded in full into every session.

When invoked 5,778 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.05778	$0.05778
Opus 5.5	$0.02311	$0.02311
Sonnet 5.5	$0.01156	$0.01156
Haiku 4.5	$0.00578	$0.00578

Measured 2mo ago against content hash df66c84def03, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

podman-mcp-server 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 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.

AGENTS.md · 625 lines

How it starts

The opening of the file, as written. The whole thing — 625 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Agents.md for Podman MCP Server

This Agents.md file provides comprehensive guidance for AI assistants and coding agents (like Claude, Gemini, Cursor, and others) to work with this codebase.

This repository contains the podman-mcp-server project, a Go-based Model Context Protocol (MCP) server that provides container management capabilities using Podman or Docker. This MCP server enables AI assistants (like Claude, Gemini, Cursor, and others) to interact with container runtimes using the Model Context Protocol (MCP).

Project Structure and Repository layout

Go package layout follows the standard Go conventions:
- cmd/podman-mcp-server/ – main application entry point.
- pkg/ – libraries grouped by domain.
  - api/ - SDK-agnostic types for tool definitions (ServerTool, ToolHandlerFunc, ToolHandlerParams).
  - config/ - Server configuration (Config struct, defaults, and override merging).
  - mcp/ - Model Context Protocol (MCP) server implementation using the official Go SDK, with tool definitions for containers, images, networks, and volumes.
  - podman/ - Podman/Docker abstraction layer with interface definition, implementation registry, CLI and REST API implementations.
  - podman-mcp-server/cmd/ - CLI command definition using Cobra framework.
  - version/ - Version information management.
- internal/test/ – shared test utilities (McpSuite, mock Podman API server).
.github/ – GitHub-related configuration (Actions workflows, Dependabot).
build/ – modular Makefile includes for packaging targets.
- node.mk – NPM packaging targets (npm-copy-binaries, npm-copy-project-files, npm-publish).
- python.mk – Python/PyPI packaging targets (python-publish).
npm/ – Node packages that wrap the compiled binaries for distribution through npmjs.com.
python/ – Python package providing a script that downloads the correct platform binary from the GitHub releases page and runs it for distribution through pypi.org.
Makefile – core build tasks; includes build/*.mk for packaging targets.
server.json – MCP Registry manifest file for publishing to the official registry.

Read the full file on GitHub · 625 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 · 625 lines · 5,778 tokens per session scan A df66c84def03

Subscribe to this mod's changes

podman-mcp-server AGENTS.md is an instructions file published in the GitHub repository manusa/podman-mcp-server (85 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 5,778 tokens to every session, about $0.0231 per session on Opus 5.5. 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 2026-08-30.

container-runtime context docker mcp model

podman-mcp-server AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
podman-mcp-server AGENTS.mdmanusa/podman-mcp-server	Instructions file	85	2mo ago	Apache-2.0	A	5,778	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	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

podman-mcp-server: Instructions file for Codex