agentmods.dev

max-mcp-server: Instructions file for Claude Code

CLAUDE.md

max-mcp-server CLAUDE.md is an instructions file for Claude Code from Digital-Crew-Technologies/max-mcp-server. It costs 1,236 tokens per session, scanned A, original, MIT.

A project-specific instruction document for a Next.js web application that provides Max Agent functions through MCP, a standard way for programs to expose callable tools. It records the repository structure, required versions, commands, tests, and deployment process.

In plain words
What is it for?
Use it when installing dependencies, running checks, testing, building, or changing the MCP server and its Next.js routes.
Why use it?
It gives a coding agent the rules needed to work in this repository without choosing the wrong package manager, command, runtime, or deployment assumption.

Instructions file for Claude Code

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

This is Digital-Crew-Technologies/max-mcp-server's own configuration. It tells Claude Code how to work on max-mcp-server 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 max-mcp-server configures →

not rated 2repo changed 11d ago A scan 1,236 tokens original MIT
View source ↗ Digital-Crew-Technologies/max-mcp-server max-mcp-server.vercel.app
Reuse

Borrowing it

Nothing to install: this file belongs to Digital-Crew-Technologies/max-mcp-server. 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/Digital-Crew-Technologies/max-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Digital-Crew-Technologies/max-mcp-server

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 max-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/digital-crew-technologies/max-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/digital-crew-technologies/max-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/digital-crew-technologies/max-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/digital-crew-technologies/max-mcp-server/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 max-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/digital-crew-technologies/max-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/digital-crew-technologies/max-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,236 This file is loaded in full into every session.
When invoked 1,236 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01236 $0.01236
Opus 5.5 $0.00494 $0.00494
Sonnet 5.5 $0.00247 $0.00247
Haiku 4.5 $0.00124 $0.00124

Measured 11d ago against content hash 99ff75812a92, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

max-mcp-server 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 11d 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 · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — max-mcp-server

The repository

  • MCP server (Streamable HTTP) that exposes Digital Crew's Max Agent API as MCP tools. Routes: app/mcp/route.ts (MCP, SSE disabled), app/chat/route.ts, app/health/route.ts.
  • Stack: Next.js 15 (App Router, output: "standalone"), mcp-handler, Zod 3, strict TypeScript, Vitest. Import alias @/* points to the root.
  • Package manager: pnpm 8.15.7, pinned by packageManager (lockfile v6). Use neither npm nor another pnpm version to change pnpm-lock.yaml.
  • Node: no .nvmrc and no engines. CI runs on Node 20.
  • Deployment: Vercel Git integration (preview on PR, production on merge to main). CI only blocks.

Commands (package.json)

  • Install: pnpm install (CI runs pnpm install --frozen-lockfile).
  • Dev: pnpm dev. Lint: pnpm lint. Typecheck: pnpm type-check (there is no typecheck script).
  • Tests: pnpm test (vitest run), pnpm test:watch.
  • Tool inventory: pnpm docs:check (checks), pnpm docs:tools (regenerates).
  • Build: pnpm build (postbuild runs scripts/copy-standalone-assets.mjs).
  • Catalog size and cap check: pnpm catalog:measure.
  • No test:security script and no format script.
  • CI order (.github/workflows/ci.yml, job legacy, required check Lint · Type-check · Test · Build): lint, type-check, test, docs:check, build, presence of .next/standalone/server.js, pnpm audit (advisory only).
  • Kit CI and security gates (KIT-02.6): ci.yml job ci and security.yml call the MANAGED inline copies kit-ci-node.yml and kit-security.yml of digitalcrew-agent-kit v0.1.0 (checks ci / ci-gate and security / security-gate). Do not edit the copies by hand; copy a newer kit tag instead.
  • pnpm verify and pnpm test:endpoints need a running server. verify without a bearer token lists the tools but skips the real calls; test:endpoints requires a token and creates and deletes real resources: do not run it without human approval.

Structure

  • app/: Next.js routes (mcp, chat, health).
  • middleware.ts (+ middleware.test.ts): authentication gateway in front of /mcp and /chat.
  • features/pilot-tools/<domain>/: one domain per folder, usually tools.ts (registration), schema.ts (Zod), repository.ts (API calls), tools.test.ts.
  • features/pilot-tools/mcp/register.ts: registration entry point and the GROUPS list (one grouped tool per domain).
  • features/pilot-tools/shared.ts, http.ts, circuit-breaker.ts, dead-letter.ts: HTTP client, retries, circuit breaker, dead-letter queue.
  • features/workspace-profile/: workspace profile tools.
  • shared/auth/, shared/http/: Max API keys, gateway scope, Digital Crew client, chat rate limit.
  • test/contract/: contract tests (inventory, catalog cap, published schemas).
  • docs/: tools.json (generated), tool reference, ADRs in docs/adr/. scripts/: docs generator and manual test scripts.

Read the full file on GitHub · 47 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. 11d ago Changed · +1 lines · +105 tokens per session 99ff75812a92
  2. 12d ago First seen · 46 lines · 1,131 tokens per session scan A 01d5b8a8611f

Subscribe to this mod's changes

max-mcp-server CLAUDE.md is an instructions file published in the GitHub repository Digital-Crew-Technologies/max-mcp-server (2 stars, last pushed 3d ago), licensed MIT. It adds 1,236 tokens to every session, about $0.0049 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 2026-10-25.

Backend and APIsBuilding agentsdigital-crewmaxmcpmcp-servernextjs
Related

max-mcp-server CLAUDE.md compared with instructions from other repositories

max-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
max-mcp-server CLAUDE.mdDigital-Crew-Technologies/max-mcp-serverInstructions file23d agoMITA1,236Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode