meraki-magic-mcp-community: Instructions file for Codex

AGENTS.md

meraki-magic-mcp-community AGENTS.md is an instructions file for Codex, OpenCode from CiscoDevNet/meraki-magic-mcp-community. It costs 467 tokens per session, scanned A, original, MIT.

A guide for setting up and running a Cisco Meraki MCP server, a service that lets an AI coding tool work with Meraki network-management APIs. It covers a dynamic server with many endpoints and a smaller manually selected server.

In plain words
What is it for?
Use it to prepare the Python environment, configure Meraki credentials, run the server locally, over HTTP, or with Docker, and test it with a Meraki sandbox.
Why use it?
It gives developers the required setup, environment variables, run commands, testing options, and security reminders in one place.

Instructions file for CodexOpenCode

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

This is CiscoDevNet/meraki-magic-mcp-community's own configuration. It tells Codex and OpenCode how to work on meraki-magic-mcp-community 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 meraki-magic-mcp-community configures →

Reuse

Borrowing it

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

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 meraki-magic-mcp-community AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ciscodevnet/meraki-magic-mcp-community/agents-md"><img src="https://agentmods.dev/badge/instructions/ciscodevnet/meraki-magic-mcp-community/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 467 This file is loaded in full into every session.
When invoked 467 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00467 $0.00467
Opus 5.5 $0.00187 $0.00187
Sonnet 5.5 $0.00093 $0.00093
Haiku 4.5 $0.00047 $0.00047

Measured 1mo ago against content hash 66688b141e6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

meraki-magic-mcp-community 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 1mo 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 · 61 lines

What it actually says

Meraki Magic MCP - Agent Guide

Dev environment tips

  • Python version: Use Python 3.13+.

  • Virtual env (recommended):

    python3 -m venv .venv
    source .venv/bin/activate
    python -m pip install -U pip
    pip install -r requirements.txt
    
  • Environment setup: Do not use a project .env file. Set MERAKI_API_KEY (required) and optional vars such as MERAKI_ORG_ID in the MCP client env block, or export them in the process environment:

    export MERAKI_API_KEY="your_api_key_here"
    export MERAKI_ORG_ID="your_org_id_here"
    

Quick run examples

# Run the dynamic MCP server (recommended, ~804 endpoints)
python meraki-mcp-dynamic.py

# Run the manual MCP server (40 curated endpoints)
python meraki-mcp.py

# Run over HTTP transport
MCP_TRANSPORT=http python meraki-mcp-dynamic.py

# Run with Docker (requires MERAKI_API_KEY in the host environment)
docker compose up -d

Testing instructions

PR instructions

  • Security: Do not commit real credentials or tokens. Use placeholders and document required env vars. Pass secrets through the MCP client env block or the process environment; never commit them.

Contribution conventions

  • Backward compatibility: Do not change existing sample behavior unless clearly improving or fixing a bug; document changes.
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. 1mo ago Changed · +63 tokens per session 66688b141e6f
  2. 2mo ago First seen · 61 lines · 404 tokens per session scan A 66f85d7d9614

Subscribe to this mod's changes

meraki-magic-mcp-community AGENTS.md is an instructions file published in the GitHub repository CiscoDevNet/meraki-magic-mcp-community (47 stars, last pushed 21d ago), licensed MIT. It adds 467 tokens to every session, about $0.0019 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.

Related

meraki-magic-mcp-community AGENTS.md compared with instructions from other repositories

meraki-magic-mcp-community AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
meraki-magic-mcp-community AGENTS.mdCiscoDevNet/meraki-magic-mcp-communityInstructions file4721d agoMITA467Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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