What is mcp-hey CLAUDE.md?

Development instructions for a local MCP server that gives Claude read and write access to Hey.com email accounts. MCP is a standard way for an AI agent to use external tools.

For developing, testing, documenting, and maintaining the Hey.com email MCP server.

It gives contributors the project structure, technologies, commands, security notes, and workflow needed to change the server consistently.

How Sealjay/mcp-hey configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Sealjay/mcp-hey. 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/Sealjay/mcp-hey/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Sealjay/mcp-hey

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/sealjay/mcp-hey/claude-md/github.svg)](https://agentmods.dev/instructions/sealjay/mcp-hey/claude-md)

Your own site

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

Per session 605 This file is loaded in full into every session.

When invoked 605 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	$0.00605	$0.00605
Opus 5.5	$0.00242	$0.00242
Sonnet 5.5	$0.00121	$0.00121
Haiku 4.5	$0.00060	$0.00060

Measured 20d ago against content hash 711e2359bf13, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-hey 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 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.

CLAUDE.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hey.com MCP Server

Local MCP server giving Claude read/write access to Hey.com via reverse-engineered web APIs and browser-identical HTTP requests. File layout: README.md. Tool surface: docs/TOOLS.md. Endpoints: docs/API.md.

Architecture

MCP server (src/index.ts): Bun, TypeScript strict, @modelcontextprotocol/server v2 low-level Server with tools/list / tools/call handlers. serveStdio picks the protocol era (2026-07-28 or 2025 initialize) per connection. Exits when stdin closes.
Auth helper (auth/hey-auth.py): Python/pywebview, spawned on demand; writes session cookies to data/hey-cookies.json (mode 600).
Cache (src/cache/): SQLite for messages, threads and search.
Sender groups (src/sender-groups.ts, src/contact-box.ts, src/sender-group-filter.ts): sender_group on message results from each sender's Hey delivery setting, and the optional group filter. Lookups cost Hey requests, so by default only filtered calls make them.

Commands

Always bun, never npm.

bun run dev              # run the server
bun test                 # all tests; bun test -t "name" for one suite
bun run lint             # Biome check
bun run format           # Biome fix
bunx tsc --noEmit        # type check
uv run ruff check . && uv run ruff format .   # Python helper

Rules

Correctness over backward compatibility. Fix the behaviour and the docs; don't add workarounds for broken parameter types.
Every request carries realistic browser headers. Fetch a fresh CSRF token before writes. Back off on x-ratelimit.
Never store credentials, only session cookies. Validate the session on startup and before sensitive operations.
Tool descriptions and annotations follow .claude/rules/mcp-tool-descriptions.md.

Hey API changes

The API is reverse-engineered and changes without notice. When you touch an endpoint, record the actual traffic (URL, method, parameters, response codes, cookie names, enum values from the UI) in docs/API.md and its changelog. Check that changelog before assuming an endpoint still works.

Read the full file on GitHub · 39 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 · +1 lines · +66 tokens per session 711e2359bf13
21d ago Changed · -110 lines · -565 tokens per session eff32903efa5
2mo ago First seen · 148 lines · 1,104 tokens per session scan A 50f0bc3535a0

Subscribe to this mod's changes

mcp-hey CLAUDE.md is an instructions file published in the GitHub repository Sealjay/mcp-hey (13 stars, last pushed 20d ago), licensed MIT. It adds 605 tokens to every session, about $0.0024 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.

TypeScript ai-agents email hey-email mcp model-context-protocol

mcp-hey CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-hey CLAUDE.mdSealjay/mcp-hey	Instructions file	13	20d ago	MIT	A	605	Claude Code
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

mcp-hey: Instructions file for Claude Code