openfoodfacts-mcp-server: Instructions file for Codex

AGENTS.md

openfoodfacts-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from cyanheads/openfoodfacts-mcp-server. It costs 7,839 tokens per session, scanned A, a copy of obsidian-mcp-server AGENTS.md, Apache-2.0.

An AGENTS.md instruction file for developing the openfoodfacts-mcp-server, which lets coding agents look up food product data. It documents the server's rules, patterns, and configuration.

In plain words
What is it for?
Building or changing this MCP server while following its framework and development rules.
Why use it?
It gives Codex and other compatible agents the project's conventions for errors, logs, stored data, user input, secrets, and issue work.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is cyanheads/openfoodfacts-mcp-server's own configuration. It tells Codex and OpenCode how to work on openfoodfacts-mcp-server 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 openfoodfacts-mcp-server configures →

Reuse

Borrowing it

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

agentmods badge for openfoodfacts-mcp-server AGENTS.md

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

agentmods 80×15 button for openfoodfacts-mcp-server AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cyanheads/openfoodfacts-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/openfoodfacts-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,839 This file is loaded in full into every session.
When invoked 7,839 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 81% copy Near-identical to another mod 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 $0.07839 $0.07839
Opus 5.5 $0.03136 $0.03136
Sonnet 5.5 $0.01568 $0.01568
Haiku 4.5 $0.00784 $0.00784

Measured yesterday against content hash 3599af3b6618, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openfoodfacts-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 yesterday.

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.

Origin

This is a copy

81% identical to obsidian-mcp-server AGENTS.md — 382 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 405 lines

How it starts

The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Protocol

Server: openfoodfacts-mcp-server Version: 0.4.0 Framework: @cyanheads/mcp-ts-core ^0.13.18 Engines: Bun ≥1.4.0, Node ≥24.0.0 MCP SDK: @modelcontextprotocol/server ^2.4.0 Zod: ^4.6.7

Read the framework docs first: node_modules/@cyanheads/mcp-ts-core/CLAUDE.md contains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.


Core Rules

  • Logic throws, framework catches. Tool/resource handlers are pure — throw on failure, no try/catch. Plain Error is fine; the framework catches, classifies, and formats. Use error factories (notFound(), validationError(), etc.) when the error code matters.
  • Use ctx.log for request-scoped logging. No console calls.
  • Use ctx.state for tenant-scoped storage. Never access persistence directly.
  • Need input the caller didn't supply? return ctx.requestInput(...) and read ctx.inputs when the handler is re-entered. Never await for user input mid-handler.
  • Secrets in env vars only — never hardcoded.
  • Cut noise. Add only what earns its place: no speculative generality, no guards for states the framework already prevents (Zod-validated params, classified errors), no abstraction until a third caller proves it, no option nothing sets.
  • Close the loop on issues. When implementing work tracked by a GitHub issue, comment on the issue with what landed and close it. Do both — a comment without a close leaves stale issues open; a close without a comment leaves no record of what shipped. The comment is for future readers — state the concrete changes, not the conversation that produced them.

Patterns

Tool

import { tool, z } from '@cyanheads/mcp-ts-core';
import { JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors';
import { getOpenFoodFactsService } from '@/services/openfoodfacts/openfoodfacts-service.js';
import { BARCODE_PATTERN } from '@/services/openfoodfacts/types.js';

export const offGetProduct = tool('off_get_product', {
  description: 'Fetch a packaged food product by barcode (4–40 digits).',
  annotations: { readOnlyHint: true },
  input: z.object({
    barcode: z.string().regex(BARCODE_PATTERN).describe('Product barcode, digits only: 4–40 digits after any leading zeros.'),
    fields: z.array(z.enum(['product_name', 'brands', 'nutriscore_grade', 'nutriments'])).optional()
      .describe('Subset of fields to return. Omitting returns all standard fields.'),
  }),
  output: z.object({
    barcode: z.string().describe('The input barcode, echoed back unchanged.'),
    // No `found` flag: a missing record is the thrown not_found error, so a boolean here could
    // only ever be true. Don't advertise a state the handler cannot return — a caller that
    // branches on it never handles the path that actually fires.
    product: z.object({ /* ... */ }).describe('Product data. Always present on success.'),
  }),
  errors: [
    {
      reason: 'not_found',
      code: JsonRpcErrorCode.NotFound,
      when: 'Open Food Facts answers HTTP 404 or status 0 for the barcode — no contributor has recorded it',
      recovery: 'Try off_search_products with the product name or brand to find the correct barcode.',
    },
  ],

  async handler(input, ctx) {
    const svc = getOpenFoodFactsService();
    const product = await svc.getProduct(input.barcode, ctx);
    if (!product) {
      throw ctx.fail('not_found', `Barcode ${input.barcode} not found`);
    }
    return { barcode: input.barcode, product };
  },

  format: (result) => [{
    type: 'text',
    text: `**${result.product.product_name ?? 'Unknown'}** (${result.barcode})`,
  }],
});

Read the full file on GitHub · 405 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. yesterday Changed · +13 lines · +780 tokens per session 3599af3b6618
  2. 4d ago Changed 9de5638855f4
  3. 15d ago Changed 093d6092d4bb
  4. 21d ago Changed · +16 lines · +407 tokens per session fee13d1dcf3f
  5. 1mo ago Changed · +3 lines · +102 tokens per session 3f73491e1dc8
  6. 1mo ago Changed · +27 lines · +1,159 tokens per session b8333481f7dd
  7. 2mo ago First seen · 346 lines · 5,391 tokens per session scan A be7334f2caf3

Subscribe to this mod's changes

openfoodfacts-mcp-server AGENTS.md is an instructions file published in the GitHub repository cyanheads/openfoodfacts-mcp-server (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 7,839 tokens to every session, about $0.0314 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 81% identical to obsidian-mcp-server AGENTS.md, differing in 382 lines, and is treated as a copy.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens