SkillAgentSearch skills...

BackendMax

🩺 AI-powered backend diagnostic MCP server. Understands what you're building and makes sure it actually works. Cross-boundary contract verification, living API docs, issue lifecycle tracking.

Install / Use

claude mcp add rish-e -- npx -y github:rish-e/BackendMax

If the server publishes to npm under a different name, use that package instead β€” check the repo README.

About this skill
πŸ”Œ

MCP Server

Model Context Protocol server

Quality Score

78/100

Category

Legal

Supported Platforms

Claude Code
Claude Desktop

Our assessment of BackendMax

BackendMax scores 78/100 on our quality scale, 188th of 205 Legal skills we index.

Its MCP Server is 26 KB long, well organised into 42 sections with 21 code examples: a thorough specification that gives an agent plenty to work with.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
3/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 6 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • Our last check on 2026-09-23 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 90/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit β€” read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-06. Automated pattern scan on 2026-10-06. It catches known dangerous patterns, not every risk β€” read a skill before letting an agent act on it.

BackendMax compared with similar skills

All 4 of these similar skills score higher than BackendMax; compare them before choosing.

SkillScoreStarsUpdatedFormat
BackendMax (this skill)by rish-e7836mo agoMCP Server
Agent-Reachby Panniantong100110.0ktodayCLAUDE.md
headroomby headroomlabs-ai10079.1ktodayCLAUDE.md
CowAgentby zhayujie10047.8k1d agoCLAUDE.md
Scraplingby D4Vinci10099.4k2d agoMCP Server

Frequently asked questions

How do I install BackendMax?
Run claude mcp add rish-e -- npx -y github:rish-e/BackendMax. The install tabs above show the steps for each supported agent.
Which AI agents does BackendMax work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is BackendMax safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 90/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is BackendMax still maintained?
The repository was last updated about 6 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
<div align="center">
╔══════════════════════════════════════════════════════════════╗
β•‘                                                              β•‘
β•‘   β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•—  β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•—  β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•—β–ˆβ–ˆβ•—  β–ˆβ–ˆβ•—β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•—β–ˆβ–ˆβ–ˆβ•—   β–ˆβ–ˆβ•—β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•— β•‘
β•‘   β–ˆβ–ˆβ•”β•β•β–ˆβ–ˆβ•—β–ˆβ–ˆβ•”β•β•β–ˆβ–ˆβ•—β–ˆβ–ˆβ•”β•β•β•β•β•β–ˆβ–ˆβ•‘ β–ˆβ–ˆβ•”β•β–ˆβ–ˆβ•”β•β•β•β•β•β–ˆβ–ˆβ–ˆβ–ˆβ•—  β–ˆβ–ˆβ•‘β–ˆβ–ˆβ•”β•β•β–ˆβ–ˆβ•—β•‘
β•‘   β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•”β•β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•‘β–ˆβ–ˆβ•‘     β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•”β• β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•—  β–ˆβ–ˆβ•”β–ˆβ–ˆβ•— β–ˆβ–ˆβ•‘β–ˆβ–ˆβ•‘  β–ˆβ–ˆβ•‘β•‘
β•‘   β–ˆβ–ˆβ•”β•β•β–ˆβ–ˆβ•—β–ˆβ–ˆβ•”β•β•β–ˆβ–ˆβ•‘β–ˆβ–ˆβ•‘     β–ˆβ–ˆβ•”β•β–ˆβ–ˆβ•— β–ˆβ–ˆβ•”β•β•β•  β–ˆβ–ˆβ•‘β•šβ–ˆβ–ˆβ•—β–ˆβ–ˆβ•‘β–ˆβ–ˆβ•‘  β–ˆβ–ˆβ•‘β•‘
β•‘   β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•”β•β–ˆβ–ˆβ•‘  β–ˆβ–ˆβ•‘β•šβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•—β–ˆβ–ˆβ•‘  β–ˆβ–ˆβ•—β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•—β–ˆβ–ˆβ•‘ β•šβ–ˆβ–ˆβ–ˆβ–ˆβ•‘β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•”β•β•‘
β•‘   β•šβ•β•β•β•β•β• β•šβ•β•  β•šβ•β• β•šβ•β•β•β•β•β•β•šβ•β•  β•šβ•β•β•šβ•β•β•β•β•β•β•β•šβ•β•  β•šβ•β•β•β•β•šβ•β•β•β•β•β•β•‘
β•‘                                                              β•‘
β•‘           β–ˆβ–ˆβ–ˆβ•—   β–ˆβ–ˆβ–ˆβ•— β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•— β–ˆβ–ˆβ•—  β–ˆβ–ˆβ•—                        β•‘
β•‘           β–ˆβ–ˆβ–ˆβ–ˆβ•— β–ˆβ–ˆβ–ˆβ–ˆβ•‘β–ˆβ–ˆβ•”β•β•β–ˆβ–ˆβ•—β•šβ–ˆβ–ˆβ•—β–ˆβ–ˆβ•”β•                        β•‘
β•‘           β–ˆβ–ˆβ•”β–ˆβ–ˆβ–ˆβ–ˆβ•”β–ˆβ–ˆβ•‘β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ•‘ β•šβ–ˆβ–ˆβ–ˆβ•”β•                         β•‘
β•‘           β–ˆβ–ˆβ•‘β•šβ–ˆβ–ˆβ•”β•β–ˆβ–ˆβ•‘β–ˆβ–ˆβ•”β•β•β–ˆβ–ˆβ•‘ β–ˆβ–ˆβ•”β–ˆβ–ˆβ•—                         β•‘
β•‘           β–ˆβ–ˆβ•‘ β•šβ•β• β–ˆβ–ˆβ•‘β–ˆβ–ˆβ•‘  β–ˆβ–ˆβ•‘β–ˆβ–ˆβ•”β• β–ˆβ–ˆβ•—                        β•‘
β•‘           β•šβ•β•     β•šβ•β•β•šβ•β•  β•šβ•β•β•šβ•β•  β•šβ•β•                        β•‘
β•‘                                                              β•‘
β•šβ•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•

🩺 AI-Powered Backend Diagnostics for Claude Code

The backend bugs your linter can't see. The contract drift your tests don't cover. Caught before deploy.

<br />

MIT License Version Node TypeScript MCP

<br />

Quick Start Β· Features Β· Tools Β· Roadmap

</div> <!-- ═══════════════════════════════════════════════════════════ --> <br />

πŸ€” What Is This?

Backend Max is a Model Context Protocol (MCP) server that gives Claude deep diagnostic vision into your backend. It statically analyzes your codebase β€” both frontend and backend β€” to surface bugs, contract drift, missing validation, security gaps, and performance anti-patterns that no other single tool catches.

Think of it as a senior backend engineer that reviews every route, checks every contract, and never goes on vacation.

<br /> <!-- ═══════════════════════════════════════════════════════════ -->

πŸ”­ How It Works

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚                                                                     β”‚
β”‚   πŸ“‚ Your Codebase          🩺 Backend Max           πŸ“‹ Report     β”‚
β”‚                                                                     β”‚
β”‚   β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”             β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”        β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  β”‚
β”‚   β”‚ Frontend   │────────▢   β”‚  Cross-       β”‚        β”‚ Health    β”‚  β”‚
β”‚   β”‚ API Calls  β”‚            β”‚  Boundary     │──────▢ β”‚ Score     β”‚  β”‚
β”‚   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜             β”‚  Analysis     β”‚        β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€  β”‚
β”‚                             β”‚              β”‚        β”‚ Issues    β”‚  β”‚
β”‚   β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”             β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚        β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€  β”‚
β”‚   β”‚ Backend   │────────▢   β”‚  β”‚ 6 Audit  β”‚ │──────▢ β”‚ API Docs  β”‚  β”‚
β”‚   β”‚ Routes    β”‚            β”‚  β”‚ Engines  β”‚ β”‚        β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€  β”‚
β”‚   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜             β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚        β”‚ Fixes     β”‚  β”‚
β”‚                             β”‚              β”‚        β”‚ Guide     β”‚  β”‚
β”‚   β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”             β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚        β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β”‚
β”‚   β”‚ Config    │────────▢   β”‚  β”‚ Intent   β”‚ β”‚                       β”‚
β”‚   β”‚ & Env     β”‚            β”‚  β”‚ Engine   β”‚ β”‚                       β”‚
β”‚   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜             β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚                       β”‚
β”‚                             β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜                       β”‚
β”‚                                                                     β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
<br /> <!-- ═══════════════════════════════════════════════════════════ -->

⚑ Why Backend Max?

Existing tools catch syntax errors and type mismatches. Backend Max catches the bugs that ship to production.

| Bug Category | TypeScript | ESLint | Jest/Vitest | Backend Max | |:---|:---:|:---:|:---:|:---:| | Frontend calls /api/user but backend exposes /api/users | ❌ | ❌ | ❌ | βœ… | | Frontend sends { name } but backend expects { username } | ❌ | ❌ | ❌ | βœ… | | Route handler missing try/catch | ❌ | ❌ | ❌ | βœ… | | Zod schema missing on POST route | ❌ | ❌ | ❌ | βœ… | | process.env.SECRET used but not in .env | ❌ | ❌ | ❌ | βœ… | | Auth middleware missing on sensitive route | ❌ | ❌ | ❌ | βœ… | | N+1 query in a loop | ❌ | ❌ | ❌ | βœ… | | API docs out of date | ❌ | ❌ | ❌ | βœ… |

πŸ’‘ Backend Max doesn't replace your existing tools. It catches what they architecturally cannot β€” cross-boundary issues that require understanding both sides of the stack.

<br /> <!-- ═══════════════════════════════════════════════════════════ -->

πŸš€ Quick Start

Install with your MCP client

<details> <summary><strong>Claude Code (recommended)</strong></summary>
claude mcp add backend-max -- npx -y backend-max

Done. Open any project and type /backendmax run a full diagnosis.

</details> <details> <summary><strong>Claude Desktop</strong></summary>

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "backend-max": {
      "command": "npx",
      "args": ["-y", "backend-max"]
    }
  }
}
</details> <details> <summary><strong>VS Code / Cursor</strong></summary>

Add to .vscode/settings.json:

{
  "mcp.servers": {
    "backend-max": {
      "command": "npx",
      "args": ["-y", "backend-max"]
    }
  }
}
</details> <details> <summary><strong>Windsurf</strong></summary>

Add to your MCP config:

{
  "mcpServers": {
    "backend-max": {
      "command": "npx",
      "args": ["-y", "backend-max"]
    }
  }
}
</details> <details> <summary><strong>From source (for development)</strong></summary>
git clone https://github.com/rish-e/backend-max.git
cd backend-max
npm install && npm run build

Then add to your MCP client config:

{
  "command": "node",
  "args": ["/path/to/backend-max/dist/server.js"]
}
</details>

Run Your First Diagnosis

Open your MCP client in any project and ask:

/backendmax run a full diagnosis on my project

That's it. Backend Max will analyze your project and return a full diagnostic report with health score, issues, and fix suggestions.

4. CI/CD Mode (Optional)

Run diagnostics from the command line or GitHub Actions:

# Basic diagnosis
npx backend-max-cli diagnose ./my-project

# CI mode β€” fail if health score drops below 75 or critical issues found
npx backend-max-cli diagnose ./my-project --ci --min-score 75 --fail-on critical

# Output formats
npx backend-max-cli diagnose ./my-project --format markdown  # PR comments
npx backend-max-cli diagnose ./my-project --format sarif     # GitHub Code Scanning
npx backend-max-cli diagnose ./my-project --format json      # Raw data
<br /> <!-- ═══════════════════════════════════════════════════════════ -->

πŸ”¬ Features Deep Dive

πŸ†• v2.4 β€” External Audit Suite (Black-Box Testing)

Audit any website with just a URL β€” no source code, no credentials, no access needed.

| Tool | Description | |------|-------------| | πŸ”’ audit_headers | HTTP security header analysis with A-F grading. Deep CSP parsing (unsafe-inline/eval, wildcards), HSTS validation (max-age, preload), COEP/COOP/CORP checks | | 🌐 audit_cors | CORS misconfiguration detection. Tests origin reflection, wildcard + credentials conflicts, overly permissive methods, missing preflight cache | | πŸ” audit_ssl | TLS/certificate analysis. Chain validation, expiry warnings, protocol version check (TLS 1.2+), cipher grading, HTTPβ†’HTTPS redirect | | πŸͺ audit_cookies | Cookie security flags audit. Checks Secure, HttpOnly, SameSite on all cookies. Detects exposed session tokens | | 🌍 audit_dns | DNS & infrastructure fingerprinting. CDN detection, SPF/DMARC/CAA records, email security posture | | πŸ’₯ probe_error_handling | Error response probing. Tests for stack trace leakage, framework disclosure, database errors, debug mode exposure | | πŸ”‘ audit_auth_flow | Authentication surface analysis. Discovers login endpoints, detects auth mechanisms, tests rate limiting, checks account enumeration | | πŸ” scan_public_api | API surface discovery. Extracts endpoints from frontend JS bundles, maps auth requirements, finds unprotected APIs |

# Audit any website β€” no source code needed
Use audit_headers on https://example.com
Use scan_public_api on https://example.com

v2.2 β€” Tier 2 Feature Drop

| Feature | Description | |---------|-------------| | ⚑ Fastify Support | Full route analysis with built-in JSON Schema validation detection, error handler checks, param extraction | | πŸ”₯ Hono Support | Route analysis with basePath resolution, zValidator detection, middleware arg parsing | | 🚦 Rate Limiting Audit | Detects rate limiting packages/patterns, flags unprotected auth endpoints, checks caching coverage | | πŸ“ API Versioning | Detects path/header versioning, finds version gaps, flags inconsistent versioning | | πŸ”— Middleware Visualization | Maps global/inline middleware chains per route, checks ordering, generates markdown visualization | | πŸ” Multi-Layer Type Tracing | Traces types across frontend β†’ route β†’ service β†’ repository β†’ DB, finds cross-layer mismatches |

v2.1 β€” Tier 1 Feature Drop

| Feature | Description | |---------|-------------| | πŸ”§ Auto-Fix Engine | Generates real unified diff patches for common issues β€” try/catch wrapping, Zod validation, auth guards, pagination. Apply with git apply | | πŸ‘οΈ Watch Mode | Incremental analysis β€” shows new issues, fixed issues, and health score delta since last run. No full re-scan needed | | πŸ”€ tRPC Support | Full router analysis β€” procedures, input validation, protected/public, queries vs mutations. 3 tRPC-specific checks | | πŸ•ΈοΈ GraphQL Analysis | Resolver scanning for Apollo, Yoga, Mercurius, type-graphql, NestJS. N+1 detection, auth checks, input validation | | πŸ“¦ Dependency Scanner | Built-in vulnerability database (12+ packages), deprecated package detection, lock file checks, npm audit integration |

v2.0 Features

| Feature | Description | |---------|-------------| | πŸ—„οΈ Prisma Schema Integration | Parses your .prisma schema and cross-references every database call β€” catches nonexistent models, fields, and missing indexes | | πŸ” Deep Type Flow Analysis | Traces frontend response variables to check property access against backend return types β€” catches data.user.firstName vs data.user.first_name | | ⚑ Server Actions | Full audit of Next.js Server Actions ('use server') β€” validation, auth, error handling, database patterns | | πŸš€ CI/CD Mode | CLI entry point with --ci, --min-score, --fail-on, and 4 output formats (text, markdown, JSON, SARIF) | | 🟒 Express.js Support | Route scanning, middleware detection, Express-specific checks (error middleware, 404, helmet/CORS) | | πŸ“„ Pages Router | Next.js Pages Router API routes (pages/api/) fully supported | | πŸ§ͺ Live Testing | Optional HTTP endpoint testing against running dev server (GET-only, safety-first) | | πŸ•ΈοΈ API Graph | Queryable relationship graph β€” ask "unprotected routes" or "routes writing to users" | | πŸ“Š Pattern Learning | Local cross-project pattern tracking β€” identifies the most common issues across your projects | | πŸ“‹ SARIF Output | GitHub Code Scanning integration via SARIF format |

<br />

Truncated for display β€” read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars3
CategoryLegal
Updated5mo ago
Forks0

Languages

TypeScript

Trust signals

90/100

From repository metadata: license, adoption, age and documentation. Not a code audit β€” see the Safety scan above for what the skill file itself contains.

1 low1 info
BackendMax β€” MCP Server: Install & Safety Check | SkillAgent