mcp-redfish: Instructions file for Codex

AGENTS.md

mcp-redfish AGENTS.md is an instructions file for Codex, OpenCode from nokia/mcp-redfish. It costs 2,752 tokens per session, scanned C, original, BSD-3-Clause.

Project instructions for nokia/mcp-redfish, a Python server that lets an AI interact with infrastructure through Redfish APIs, a standard way to manage hardware such as servers.

In plain words
What is it for?
Use them when installing dependencies, running the Redfish MCP server, preparing pre-commit checks, or running tests, linting, formatting, and type checks.
Why use it?
They give developers a consistent setup, testing, formatting, and type-checking process for the project.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is nokia/mcp-redfish's own configuration. It tells Codex and OpenCode how to work on mcp-redfish itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-redfish configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nokia/mcp-redfish. 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/nokia/mcp-redfish/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/nokia/mcp-redfish

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 mcp-redfish AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nokia/mcp-redfish/agents-md/github.svg)](https://agentmods.dev/instructions/nokia/mcp-redfish/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nokia/mcp-redfish/agents-md"><img src="https://agentmods.dev/badge/instructions/nokia/mcp-redfish/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.

agentmods 80×15 button for mcp-redfish AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nokia/mcp-redfish/agents-md"><img src="https://agentmods.dev/badge/instructions/nokia/mcp-redfish/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,752 This file is loaded in full into every session.
When invoked 2,752 The same file — it is already loaded in full.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02752 $0.02752
Opus 5.5 $0.01101 $0.01101
Sonnet 5.5 $0.00550 $0.00550
Haiku 4.5 $0.00275 $0.00275

Measured 2mo ago against content hash 5c39bfeb34a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

mcp-redfish AGENTS.md scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf .venv/
AGENTS.md · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project Overview

The Redfish MCP Server is a Python-based Model Context Protocol (MCP) server that provides a natural language interface for managing infrastructure via Redfish APIs. It uses FastMCP framework and integrates with the Python Redfish library to enable AI agents to interact with Redfish-enabled infrastructure components.

Key Technologies:

  • Python 3.14 recommended; Python 3.13 supported but deprecated (runtime policy)
  • FastMCP framework
  • Python Redfish library
  • uv for dependency management
  • pytest for testing
  • ruff for linting and formatting
  • mypy for type checking

Development Environment Setup

Quick Start

# Clone and install dependencies
make install  # or 'make dev' for development setup with pre-commit hooks

# Install development dependencies only
make install-dev

# Install test dependencies
make install-test

Using uv directly

# Create virtual environment and install dependencies
uv venv
source .venv/bin/activate
uv sync --extra dev --extra test

Pre-commit Setup

make pre-commit-install  # Install pre-commit hooks
make pre-commit-update   # Update hooks to latest versions
make pre-commit-run      # Run hooks on all files

Build and Test Commands

Running the Server

# Recommended: Run with console script
uv run mcp-redfish
# OR use Makefile shortcut:
make run-stdio

# Alternative transports
# Breaking change: HTTP MCP transports (sse, streamable-http) now require
# authentication. Set MCP_AUTH_MODE (and the matching MCP_AUTH_* variables),
# or set MCP_HTTP_AUTH=false to keep unauthenticated HTTP. stdio is unchanged.
# make run-sse / make run-streamable-http will not start without that env.
# Prefer streamable-http. Non-loopback binds also require exact values in
# FASTMCP_HTTP_ALLOWED_HOSTS. See docs/MCP_AUTH.md for authentication and
# docs/MCP_HTTP_DEPLOYMENT.md for listener, TLS, and deployment settings.
# JWTs require exp and enforce nbf/future iat. Introspection additionally
# requires MCP_AUTH_INTROSPECTION_ISSUER and MCP_AUTH_INTROSPECTION_AUDIENCE;
# private IdPs require the warned MCP_AUTH_INTROSPECTION_ALLOW_PRIVATE=true.
# Loopback/private JWKS (OIDC Proxy, JWT JWKS) requires the warned
# MCP_AUTH_JWKS_ALLOW_PRIVATE=true.
# Non-loopback SSE is refused unless the legacy break-glass setting
# MCP_ALLOW_REMOTE_SSE=true is explicitly set; prefer streamable-http.
make run-sse              # Server-Sent Events transport (fail-closed without auth env)
make run-streamable-http  # Streamable HTTP transport (fail-closed without auth env)

# Development/CI: Run as module
uv run python -m src.main

# Debug with MCP Inspector
make inspect

Read the full file on GitHub · 358 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. 2mo ago Changed · +7 lines · +120 tokens per session 5c39bfeb34a5
  2. 2mo ago Changed · +17 lines · +413 tokens per session 7e97ae61eb12
  3. 2mo ago First seen · 334 lines · 2,219 tokens per session scan C 967a40ec5ee9

Subscribe to this mod's changes

mcp-redfish AGENTS.md is an instructions file published in the GitHub repository nokia/mcp-redfish (20 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 2,752 tokens to every session, about $0.0110 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

mcp-redfish AGENTS.md compared with instructions from other repositories

mcp-redfish AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-redfish AGENTS.mdnokia/mcp-redfishInstructions file201mo agoBSD-3-ClauseC2,752Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode