missingmcp: Instructions file for Claude Code

CLAUDE.md

missingmcp CLAUDE.md is an instructions file for Claude Code from VelkyVenik/missingmcp. It costs 5,579 tokens per session, scanned A, original, MIT.

Repository instructions for missingmcp, a gateway that lets several trusted users connect their service accounts to Claude through the Model Context Protocol (MCP), a standard way for AI tools to use external services.

In plain words
What is it for?
Use it when working on missingmcp, including its OAuth login, encrypted account storage, service adapters, MCP forwarding, and tests.
Why use it?
It gives the coding agent the project’s purpose, architecture, commands, and testing details, reducing mistakes when changing or running the gateway.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is VelkyVenik/missingmcp's own configuration. It tells Claude Code how to work on missingmcp 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 missingmcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to VelkyVenik/missingmcp. 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/VelkyVenik/missingmcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/VelkyVenik/missingmcp

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.

agentmods badge for missingmcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/velkyvenik/missingmcp/claude-md/github.svg)](https://agentmods.dev/instructions/velkyvenik/missingmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/velkyvenik/missingmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/velkyvenik/missingmcp/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.

agentmods 80×15 button for missingmcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/velkyvenik/missingmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/velkyvenik/missingmcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,579 This file is loaded in full into every session.
When invoked 5,579 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.05579 $0.05579
Opus 5.5 $0.02232 $0.02232
Sonnet 5.5 $0.01116 $0.01116
Haiku 4.5 $0.00558 $0.00558

Measured yesterday against content hash ee911cf7b240, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

missingmcp CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Blocking adapter sign-in runs off the event loop, capped.** `adapter.start_login` / `resume_second_factor` / `verify` do **synchronous** network I/O (garminconnect, WHOOP profile fetch); **every** call site in the as
CLAUDE.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

A multi-user, OAuth 2.1–protected remote MCP gateway that lets a small trusted circle each connect their own upstream-service accounts to Claude (mobile/desktop/web). The gateway terminates OAuth, performs the adapter-specific login — a credential form (garmin) or a redirect to the upstream's own OAuth (whoop: /whoop/oauth/callback) — stores per-account encrypted blobs, and forwards /<adapter>/mcp via one of three strategies: worker (garmin — spawns + reverse-proxies to a per-user subprocess of the unmodified garmin_mcp worker, github.com/Taxuspt/garmin_mcp), remote (no subprocess; forwards to a hosted upstream MCP, injecting the account's credentials as headers), or local (whoop — no subprocess, no shared upstream; the MCP server runs in-process, see adapters/whoop/mcp.py). No in-tree adapter uses the remote strategy today — rohlik used it until Rohlík shipped its own OAuth MCP (2026-07); the strategy stays covered by tests/test_remote_forward.py via a stub adapter.

The canonical design and the task-by-task implementation plan live in docs/superpowers/specs/ and docs/superpowers/plans/ — read them for rationale and the full data flow, but treat them as dated design records: the 2026-07-05 multi-adapter spec still describes a rohlik adapter that was implemented and then retired (2026-07-06, Rohlík ships its own OAuth MCP) — don't re-add it. Operator-facing docs (env-var reference, monitoring, deploy checklist) live in README.md; operational scripts (status, revoke, usage) live in scripts/ and are documented in README → Monitoring.

Commands

# Tests — the `--extra dev` is REQUIRED: pytest lives in [project.optional-dependencies].dev,
# so plain `uv run pytest` fails with "no module named pytest".
uv run --extra dev pytest -q                          # full suite
uv run --extra dev pytest tests/test_oauth.py -v      # one file
uv run --extra dev pytest tests/test_oauth.py::test_metadata_shape -v   # one test

# Run the gateway locally (no Garmin needed to exercise the OAuth surface).
# DATA_DIR defaults to /data (not writable locally) — point it somewhere writable.
# GATEWAY_SECRET must be >=32 chars AND must not start with "change-me" (startup guard).
# To exercise the full /<adapter>/mcp path locally, also set GARMIN_MCP_CMD (garmin-mcp isn't on
# PATH): GARMIN_MCP_CMD="uvx --python 3.12 --from git+https://github.com/Taxuspt/garmin_mcp garmin-mcp"
GATEWAY_SECRET="$(openssl rand -base64 48)" PUBLIC_URL=http://localhost:8088 PORT=8088 \
  DATA_DIR=./.localdata uv run missingmcp

# After changing adapters/whoop/mcp.py's TOOLS table, regenerate the landing
# page's tool listing:
python scripts/gen_whoop_tools.py

# After changing the link-preview card's copy or palette, redraw static/og.png
# (Pillow is not a project dependency, hence --with). The `?v=` cache-buster in
# pages.py is derived from the file's hash, so a redraw invalidates scraper caches
# by itself:
uv run --with pillow python scripts/gen_og_image.py

# Production (missingmcp.com) runs on Railway, built from the Dockerfile, and
# auto-deploys on every push to main — pushing = deploying. Verify after push:
# railway deployment list --json. (Self-host: plain `docker run` — see README.)

Read the full file on GitHub · 125 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 · +121 tokens per session ee911cf7b240
  2. 8d ago Changed · +72 tokens per session c3c2ff128368
  3. 9d ago Changed · +105 tokens per session 75beb0f77608
  4. 12d ago Changed · +1 lines · +174 tokens per session c51dff872cab
  5. 15d ago Changed · +1 lines · +128 tokens per session 4f929709bf71
  6. 19d ago Changed · +83 tokens per session 0545a89c9df6
  7. 22d ago Changed · +2 lines · +323 tokens per session 40a661c6eac9
  8. 1mo ago Changed · +122 tokens per session 7113abec2dd7
  9. 1mo ago Changed · +1 lines · +219 tokens per session bdb231432d84
  10. 1mo ago First seen · 120 lines · 4,232 tokens per session scan A 22494bbf4df5

Subscribe to this mod's changes

missingmcp CLAUDE.md is an instructions file published in the GitHub repository VelkyVenik/missingmcp (16 stars, last pushed today), licensed MIT. It adds 5,579 tokens to every session, about $0.0223 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories