What is yazio_mcp CLAUDE.md?

A set of Claude Code instructions for a project that combines a Yazio nutrition-data MCP server with a Telegram bot. It documents the project structure, environment variables, and how the two parts run together on Render, a cloud hosting service.

Use it when developing, configuring, deploying, or troubleshooting the Yazio MCP server and its Telegram nutrition bot.

It gives the coding agent the project context needed to work with the right files, settings, and startup process.

How Psilolouben/yazio_mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Psilolouben/yazio_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/Psilolouben/yazio_mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Psilolouben/yazio_mcp

Made for: Claude Code.

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/psilolouben/yazio_mcp/claude-md/github.svg)](https://agentmods.dev/instructions/psilolouben/yazio_mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/psilolouben/yazio_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/psilolouben/yazio_mcp/claude-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/psilolouben/yazio_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/psilolouben/yazio_mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,140 This file is loaded in full into every session.

When invoked 1,140 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	$0.01140	$0.01140
Opus 5	$0.00570	$0.00570
Sonnet 5	$0.00228	$0.00228
Haiku 4.5	$0.00114	$0.00114

Measured 9d ago against content hash 064bf965afee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

yazio_mcp CLAUDE.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 9d 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.

CLAUDE.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Yazio MCP + Telegram Bot

Project overview

Two components run in a single Render web service:

MCP server (mcp_server.py) — exposes Yazio nutrition data over the MCP Streamable HTTP transport at /mcp. Used by Claude Desktop via mcp-remote.
Telegram bot (telegram_bot.py) — answers nutrition questions. Uses Groq (LLaMA 3.3 70B) as the LLM and calls the MCP server for data.

On Render, mcp_server.py is the entrypoint. It starts the Telegram bot in a background daemon thread, then launches uvicorn.

Key files

mcp_server.py       FastMCP server + entrypoint
telegram_bot.py     Telegram bot (Groq + MCP client)
requirements.txt    Runtime dependencies
render.yaml         Render deployment (single web service)

Environment variables

Variable	Used by	Description
`YAZIO_EMAIL`	mcp_server.py	Yazio account email
`YAZIO_PASSWORD`	mcp_server.py	Yazio account password
`TELEGRAM_BOT_TOKEN`	telegram_bot.py	From @BotFather
`GROQ_API_KEY`	telegram_bot.py	From console.groq.com
`PORT`	mcp_server.py	Set automatically by Render
`RENDER`	mcp_server.py	Set automatically by Render; triggers HTTP mode
`RENDER_EXTERNAL_HOSTNAME`	mcp_server.py	Used for TransportSecuritySettings
`MCP_URL`	telegram_bot.py	Override MCP endpoint (default: https://yazio-mcp.onrender.com/mcp)

How the bot works

User message (Telegram)
  → ask_groq()
    → fetch MCP tool definitions (cached after first call)
    → Groq chat.completions.create() with tools
    → if tool_use: _call_tool() → MCP /mcp endpoint → Yazio API
    → loop until text response
  → reply to user

Tool definitions are fetched from the live MCP server at first message and cached in _mcp_tools. This means the bot automatically picks up any new tools added to the MCP server.

Startup flow on Render

# mcp_server.py __main__
if os.environ.get("RENDER"):
    if os.environ.get("TELEGRAM_BOT_TOKEN"):
        threading.Thread(target=bot_main, daemon=True).start()
    uvicorn.run(mcp.streamable_http_app(), host="0.0.0.0", port=PORT)
else:
    mcp.run()  # stdio mode for local Claude Desktop

Read the full file on GitHub · 97 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.

9d ago First seen · 97 lines · 1,140 tokens per session scan A 064bf965afee

Subscribe to this mod's changes

yazio_mcp CLAUDE.md is an instructions file published in the GitHub repository Psilolouben/yazio_mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,140 tokens to every session, about $0.0057 per session on Opus 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 2026-08-31.

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 tokens

yazio_mcp: Instructions file for Claude Code