# middleBrick | API-Security

middleBrick | API-Security is an MCP server for Claude Code that checks APIs for OWASP Top 10 flaws and returns a risk score. Run it before a release or while auditing an endpoint you did not write.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 2930 installs
- Author: middlebrick
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/middlebrick/api-security
- Updated: 2026-03-27
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/middlebrick-api-security

## What it does

Three tools sit behind one HTTP address. `scan_api` points the service at an endpoint and returns a risk score; `get_scan` pulls up an earlier run by id; `list_scans` shows what has already been checked. The scans look for broken object-level and function-level authorization, injection, leaked data, missing rate limits, GraphQL problems and LLM-specific issues.

Nothing runs on your machine. The target address goes to `https://api-security--middlebrick.run.tools`, so an internal API leaves your network — agree that with whoever owns the perimeter first.

Setup is a single line per client. In Claude Code it is `claude mcp add --transport http middlebrick-api-security https://api-security--middlebrick.run.tools`. Codex and Gemini CLI take the same URL through their own `mcp add`.

## Requirements
- Remote server: `https://api-security--middlebrick.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http api-security https://api-security--middlebrick.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add middlebrick-api-security --url https://api-security--middlebrick.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "middlebrick-api-security": {
            "url": "https://api-security--middlebrick.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "middlebrick-api-security": {
            "type": "http",
            "url": "https://api-security--middlebrick.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http middlebrick-api-security https://api-security--middlebrick.run.tools
```

## When to use it
- score an API against OWASP Top 10 before a release
- check object-level and function-level authorization gaps
- reopen an earlier scan by its id
- see which endpoints were already scanned
- cover GraphQL and rate-limit issues in one run

## Example prompts
- Run `scan_api` against the staging endpoint and give me the risk score.
- Show earlier runs with `list_scans`, then open the newest one with `get_scan`.
- Check the auth endpoint for access bypass and rate limiting, one-line risk verdict.

## Similar
- [api-security](https://affpapa.org/en/nevibecode/agents/api-security.md) — subagent · ★ 2482 repo stars
- [api-audit](https://affpapa.org/en/nevibecode/skills/api-audit.md) — skill · 646 installs
- [api-security-review](https://affpapa.org/en/nevibecode/skills/api-security-review.md) — skill · 684 installs
- [api-security-testing](https://affpapa.org/en/nevibecode/skills/api-security-testing.md) — skill · 121 installs
- [backend-api-security-backend-security-coder](https://affpapa.org/en/nevibecode/agents/backend-api-security-backend-security-coder.md) — subagent · ★ 42780 repo stars
- [testing-api-security-with-owasp-top-10](https://affpapa.org/en/nevibecode/skills/testing-api-security-with-owasp-top-10.md) — skill · 931 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
