What is heorth-mcp AGENTS.md?

Project instructions for heorth-mcp, an MCP server that passes requests to upstream services through their public REST APIs. A REST API is a web interface that applications use to exchange data and perform actions.

Use them when developing or reviewing heorth-mcp code, especially its TypeScript architecture, API translations, authentication, tools, and migration from the Heorth and KithLedger projects.

They define the project boundary: the server must not access upstream code or databases directly, and must only expose capabilities available through the authenticated REST API.

How Wyrhta-Labs/heorth-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Wyrhta-Labs/heorth-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/Wyrhta-Labs/heorth-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Wyrhta-Labs/heorth-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/wyrhta-labs/heorth-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/wyrhta-labs/heorth-mcp/agents-md)

Your own site

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

Per session 2,104 This file is loaded in full into every session.

When invoked 2,104 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	$0.02104	$0.02104
Opus 5.5	$0.00842	$0.00842
Sonnet 5.5	$0.00421	$0.00421
Haiku 4.5	$0.00210	$0.00210

Measured 20d ago against content hash bd43c58b7a95, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

heorth-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 20d 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 · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — heorth-mcp

The household's single MCP server, running as its own container. It owns no data and no domain logic: every tool call is translated into one or more calls against an upstream service's public REST API.

Node.js 22 + TypeScript, Hono, Zod, Vitest. No database, no ORM, no migrations.

All 56 formerly embedded tools are ported; weorc.* (7) and gewrit.* (2) and ethel.update_asset are new — 66 in all. heorth-mcp is the household's only MCP surface: the embedded MCP code is gone from Heorth, KithLedger and wyrhta-core (August 2026) — see docs/spec/migration.md.

The one rule that shapes everything

heorth-mcp is a REST client. It does not import Heorth or KithLedger code, does not touch their databases, and does not reach for anything the REST API does not already expose. If a tool needs a capability the upstream API lacks, the fix is a new REST endpoint in the upstream repo — never a shortcut from here.

This is what makes the container replaceable, the upstream services testable without MCP, and the tool surface honest: an MCP tool can only ever do what an authenticated household member could already do over HTTP.

Architecture

MCP client (Claude Desktop, Claude Code, …)
  │  Streamable HTTP, Authorization: Bearer he_...
  ▼
heorth-mcp  ── HEORTH_BASE_URL ──▶  Heorth REST   /api/v1/*   (he_ key passed through)
            ── HEORTH_BASE_URL ──▶  POST /auth/satellite-token (exchange, ADR 0009)
            ── KITH_BASE_URL   ──▶  KithLedger REST /api/v1/* (exchanged member JWT)

One process, both upstreams. The 53 Heorth tools (household.*, calendar.*, meals.*, library.*, ethel.*, weorc.*, gewrit.*, tasks.*, feoh.*) and the 13 KithLedger tools (kith.*) are served from the same endpoint.
Each upstream is optional — with one asymmetry. With HEORTH_BASE_URL unset the Heorth tools are not registered; same for KITH_BASE_URL and kith.*. But kith.* also needs Heorth, because that is where its member token is minted, so KITH_BASE_URL alone is a boot error. The container starts and serves whatever is configured, including nothing.
Transport is HTTP. Streamable HTTP is the only supported transport; stdio is not offered, not even for local dev — point a local client at the container's URL instead.

Read the full file on GitHub · 145 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.

20d ago Changed · -6 tokens per session bd43c58b7a95
1mo ago Changed · +1 lines · +37 tokens per session b9bec20cc7a5
2mo ago First seen · 144 lines · 2,073 tokens per session scan A 51a66186d3e3

Subscribe to this mod's changes

heorth-mcp AGENTS.md is an instructions file published in the GitHub repository Wyrhta-Labs/heorth-mcp (0 stars, last pushed 20d ago), licensed MIT. It adds 2,104 tokens to every session, about $0.0084 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 2026-08-31.

heorth-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
heorth-mcp AGENTS.mdWyrhta-Labs/heorth-mcp	Instructions file	0	20d ago	MIT	A	2,104	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

heorth-mcp: Instructions file for Codex