Middlebrick MCP Server

@middleBrick

Basic information

About Middlebrick MCP Server

Scan APIs for security vulnerabilities and get OWASP risk scores. Detects auth bypass, BOLA/IDOR, data exposure, prompt injection, and 12+ security categories.

#api-security#owasp #vulnerability-scanner #security #llm-security #prompt-injection #api-testing #devsecops #ci-cd #compliance #pentest

Middlebrick MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "middlebrick": {
      "command": "npx",
      "args": [
        "-y",
        "@middlebrick/mcp-server"
      ],
      "env": {
        "MIDDLEBRICK_API_KEY": "mb_your_key_here"
      }
    }
  }
}

Middlebrick MCP Server tools

Scan an API endpoint for security vulnerabilities and get a risk score

Get results of a previous middleBrick scan by its ID

List previous middleBrick API security scans

Overview

What is Middlebrick?

Middlebrick is an MCP server that integrates with middleBrick API security scanning. It lets AI assistants like Claude and Cursor scan APIs for vulnerabilities via tool calls.

How to use Middlebrick?

Install by configuring the MCP client with the command npx -y @middlebrick/mcp-server and setting the MIDDLEBRICK_API_KEY environment variable. Invoke the tools scan_api, get_scan, and list_scans from the AI assistant.

Key features of Middlebrick

Scan an API endpoint for security vulnerabilities
Retrieve results of a previous scan
List all previous scans with filtering
Configure via environment variables
Works with Claude Desktop and Cursor

Use cases of Middlebrick

AI-assisted security auditing of API endpoints
Automated vulnerability scanning during development
Retrieving and reviewing past scan results in chat

Frequently asked questions

How do I get a Middlebrick API key?

Get your API key at [middlebrick.com/dashboard](https://middlebrick.com/dashboard).

What tools does Middlebrick provide?

Three tools: `scan_api` (scan an endpoint), `get_scan` (get a scan’s results), and `list_scans` (list previous scans).

What parameters does `scan_api` require?

The `url` parameter (string) is required; `method` (string, default GET) is optional.

Can I override the API base URL?

Yes, set the `MIDDLEBRICK_BASE_URL` environment variable (optional).

What scan statuses can I filter with `list_scans`?

You can filter by `queued`, `processing`, `completed`, or `failed`.

Comments

More Developer Tools MCP servers

Mcp-Warden

ermoluk

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

Foremerge

naw103

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.