What is mcp-servers AGENTS.md?

Project instructions for a group of MCP servers that let AI assistants work with Qiskit and IBM Quantum services. Qiskit is software for creating and running programs on quantum computers.

Use it when developing or maintaining quantum-computing tools, such as circuit execution, job management, code assistance, optimization, and conversion for quantum hardware.

It explains the project's architecture, technologies, and intended workflows so an agent can make compatible changes.

How Qiskit/mcp-servers configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Qiskit/mcp-servers. 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/Qiskit/mcp-servers/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Qiskit/mcp-servers

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/qiskit/mcp-servers/agents-md/github.svg)](https://agentmods.dev/instructions/qiskit/mcp-servers/agents-md)

Your own site

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

Per session 11,715 This file is loaded in full into every session.

When invoked 11,715 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	$0.11715	$0.11715
Opus 5.5	$0.04686	$0.04686
Sonnet 5.5	$0.02343	$0.02343
Haiku 4.5	$0.01171	$0.01171

Measured 2mo ago against content hash 768bedb5c111, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-servers 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 · 1,250 lines

How it starts

The opening of the file, as written. The whole thing — 1,250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to AI development assistants when working with code in this repository.

Supported AI Assistants:

IBM Bob
Claude Code
GitHub Copilot
Cursor AI
Windsurf
Gemini CLI
Any AI assistant with codebase context awareness

Project Overview

qiskit-mcp-servers is a collection of Model Context Protocol (MCP) servers that provide AI assistants, LLMs, and agents with seamless access to IBM Quantum services and Qiskit libraries for quantum computing development and research.

Core Purpose

Enable AI systems to interact with quantum computing resources through Qiskit
Provide production-ready MCP servers for quantum computing workflows
Connect AI assistants to real quantum hardware automatically
Simplify quantum circuit execution and job management
Provide intelligent quantum code completion and assistance
Enable AI-powered quantum circuit optimization and transpilation

Key Technologies

Protocol: Model Context Protocol (MCP)
Language: Python 3.10+ (3.11+ recommended)
Framework: FastMCP (async-first MCP framework)
Package Manager: uv (modern Python package manager with workspace support)
Testing: pytest with async support, 65%+ coverage
Code Quality: ruff (formatting + linting), mypy (type checking)
Build System: hatchling with pyproject.toml

Architecture

Repository Structure

This is a monorepo using uv workspace containing five independent MCP servers:

qiskit-mcp-servers/
├── qiskit-mcp-server/                       # Core Qiskit transpilation
├── qiskit-docs-mcp-server/                  # Documentation retrieval
├── qiskit-ibm-runtime-mcp-server/           # IBM Quantum cloud services
├── qiskit-ibm-transpiler-mcp-server/        # AI-powered transpilation
├── qiskit-gym-mcp-server/                   # RL-based circuit synthesis
├── .claude/skills/                          # Claude Code skills
├── .github/                                 # GitHub templates and workflows
├── pyproject.toml                           # Workspace configuration & meta-package
├── mypy.ini                                 # Shared mypy configuration
├── ruff.toml                                # Shared ruff configuration
├── README.md                                # Main repository documentation
├── PUBLISHING.md                            # PyPI publishing guide
├── CONTRIBUTING.md                          # Contribution guidelines
├── CODE_OF_CONDUCT.md                       # Community guidelines
└── LICENSE                                  # Apache 2.0 license

Read the full file on GitHub · 1,250 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 · 1,250 lines · 11,715 tokens per session scan A 768bedb5c111

Subscribe to this mod's changes

mcp-servers AGENTS.md is an instructions file published in the GitHub repository Qiskit/mcp-servers (46 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 11,715 tokens to every session, about $0.0469 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.

mcp-servers AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-servers AGENTS.mdQiskit/mcp-servers	Instructions file	46	1mo ago	Apache-2.0	A	11,715	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	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	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mcp-servers: Instructions file for Codex