What is eonik-mcp AGENTS.md?

A local bridge that connects coding assistants to Eonik, a remote service, and can set up that connection in supported assistant applications. It uses browser sign-in rather than asking for a password or key in chat.

Use it to initialize Eonik connections, check setup status, create or select a brand, and add named competitors when supported by the account.

It avoids configuring each assistant manually and gives the agent a documented way to connect and set up a person's Eonik account.

How eonik-ai/eonik-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to eonik-ai/eonik-mcp. 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/eonik-ai/eonik-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/eonik-ai/eonik-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/eonik-ai/eonik-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/eonik-ai/eonik-mcp/agents-md)

Your own site

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

Per session 631 This file is loaded in full into every session.

When invoked 631 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	$0.00631	$0.00631
Opus 5.5	$0.00252	$0.00252
Sonnet 5.5	$0.00126	$0.00126
Haiku 4.5	$0.00063	$0.00063

Measured today against content hash a97cb20f6742, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

eonik-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 today.

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 · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

eonik, for agents

eonik's MCP server is https://api.eonik.ai/mcp (streamable HTTP, OAuth sign-in). This package, eonik-mcp, is a local bridge to it for hosts that need a local process, plus init, which connects every assistant on a computer to it.

Connect

npx eonik-mcp init            # Claude Code, VS Code, Cursor, Codex; says the Claude Desktop steps
npx eonik-mcp init --dry-run  # says what it would do, changes nothing

Or add the connector https://api.eonik.ai/mcp in the host. The person signs in to eonik in the browser the first time; never ask them for a password or a key in the chat.

Set eonik up for a person

The server's own guide is the resource eonik://guide/set-up. In short:

get_setup: where their eonik stands, their brands, their plan, and the one next step.
No brand yet: ask for the website if they have not said it, then create_brand. In ChatGPT this works before sign-in: eonik shows what it read and asks the person to sign in; then call create_brand again. Nothing else answers before sign-in. Several brands and none chosen: ask which, then use_brand.
add_competitors with every competitor they name, each as their Ads Library or Instagram link or their name exactly as said. A name comes back as the page the Ad Library shows: ask the person if it is the one, then call again with its link. Never add one they have not confirmed.
invite_teammates with the addresses they give. connect_source gives a link to the ad platform's own sign-in for the brand; give it to the person.
Making or resizing work runs in the eonik app on their Mac. When it is not open, the answer says where to install it and which account to sign in with; pass that on.

Plans and credits are said as facts by get_setup, with the page that says what each plan includes. The person chooses a plan there; an agent never buys anything.

Never

Pause, launch or edit ads; write to an ad account; predict how an ad will perform; or make a choice that is the person's (making the sizes, approving, sending). Those are buttons they press.

Read the full file on GitHub · 48 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.

today First seen · 48 lines · 631 tokens per session scan A a97cb20f6742

Subscribe to this mod's changes

eonik-mcp AGENTS.md is an instructions file published in the GitHub repository eonik-ai/eonik-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 631 tokens to every session, about $0.0025 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 2026-11-11.

Marketing and SEO ads claude codex cursor macos mcp

eonik-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
eonik-mcp AGENTS.mdeonik-ai/eonik-mcp	Instructions file	1	yesterday	MIT	A	631	Codex, OpenCode
data-scientist copilot-instructions.mdrealnghon/data-scientist	Instructions file	2	4mo ago	MIT	A	373	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
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	3,086	GitHub Copilot

eonik-mcp: Instructions file for Codex