What is amazing-marvin-mcp CLAUDE.md?

Project instructions for extending an MCP server that connects to Amazing Marvin, a task-management application. They describe how to read mirrored data, send updates through the API, and keep local data consistent.

Use them when adding tools, writable fields, document types, or workflow support to the Amazing Marvin MCP server.

They prevent unsafe direct database writes and avoid API usage patterns that could exceed limits or break conflict handling.

How tsvikas/amazing-marvin-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tsvikas/amazing-marvin-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/tsvikas/amazing-marvin-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tsvikas/amazing-marvin-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/tsvikas/amazing-marvin-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/tsvikas/amazing-marvin-mcp/claude-md)

Your own site

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

Per session 847 This file is loaded in full into every session.

When invoked 847 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	$0.00847	$0.00847
Opus 5.5	$0.00339	$0.00339
Sonnet 5.5	$0.00169	$0.00169
Haiku 4.5	$0.00085	$0.00085

Measured 2mo ago against content hash d2764a119214, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

amazing-marvin-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 2mo 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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

amazing-marvin-mcp — working rules

MCP server for Amazing Marvin. Read README.md for what it does; this file is the design rules that keep additions coherent.

Architecture rules

Reads come from the mirror, writes go through the REST API. The mirror (mirror.py) is a local copy of the CouchDB sync database kept fresh with _changes. Never add a tool that reads via REST endpoints (todayItems, children, …): they have no filtering and a 1440 requests/day budget. Never write directly to CouchDB: /api/doc/update does the fieldUpdates bookkeeping Marvin's conflict resolution needs.
Every write folds its response into the mirror (mirror.apply) so the next read is consistent without another request.
No doc/delete tool. Marvin's trash is client-side; API deletes are unrecoverable. MarvinAPI.delete_doc exists for test cleanup only.
No "smart"/opinionated tools ("what should I focus on"). Tools expose Marvin's model; the user's conventions live in their workflow Markdown (workflow.md or a workflow/ directory; templates in src/amazing_marvin_mcp/templates/workflow/), injected into the server instructions and exposed as marvin://workflow[/<section>].
Use Marvin's UI vocabulary in tool names, parameters, output fields and descriptions: Do date (day), Due date (dueDate, hard deadline), End date (endDate, self-imposed), Start date, Planned week/month, Duration estimate, Importance (P1 red = 3, P2 = 2, P3 = 1), Eat the Frog, Backburner, Master List, Inbox (parentId="unassigned"), categories vs projects (type). Don't merge due date and end date; don't call either "deadline" in a field.
Models tolerate Marvin's conventions: unset fields arrive as null, "" or 0 (timeEstimate: 0 = no estimate). Keep extra="allow" so undocumented fields pass through (get_task shows them under other_fields).
Rate limits are Marvin's ask, not ours to optimise away: ≤1 REST call per 3 s (MarvinAPI throttles), mirror polls ≤1/min.

Read the full file on GitHub · 62 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.

2mo ago First seen · 62 lines · 847 tokens per session scan A d2764a119214

Subscribe to this mod's changes

amazing-marvin-mcp CLAUDE.md is an instructions file published in the GitHub repository tsvikas/amazing-marvin-mcp (1 stars, last pushed 11d ago), licensed MIT. It adds 847 tokens to every session, about $0.0034 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.

Project management

amazing-marvin-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
amazing-marvin-mcp CLAUDE.mdtsvikas/amazing-marvin-mcp	Instructions file	1	11d ago	MIT	A	847	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

amazing-marvin-mcp: Instructions file for Claude Code