middleBrick | API-Security — MCP server: OWASP API scanning
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.
no license 2,930 installs updated 2026-03-27
claude mcp add --transport http api-security https://api-security--middlebrick.run.toolsWhat middleBrick | API-Security 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.
What it helps with
- 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 for the agent
- Run
scan_apiagainst the staging endpoint and give me the risk score. - Show earlier runs with
list_scans, then open the newest one withget_scan. - Check the auth endpoint for access bypass and rate limiting, one-line risk verdict.
How to install middleBrick | API-Security
Platform CLI: remote server
claude mcp add --transport http api-security https://api-security--middlebrick.run.toolsPlatform CLI: remote server
codex mcp add middlebrick-api-security --url https://api-security--middlebrick.run.toolsConfig file
{
"mcpServers": {
"middlebrick-api-security": {
"url": "https://api-security--middlebrick.run.tools"
}
}
}Config file
{
"servers": {
"middlebrick-api-security": {
"type": "http",
"url": "https://api-security--middlebrick.run.tools"
}
}
}Platform CLI: remote server
gemini mcp add -t http middlebrick-api-security https://api-security--middlebrick.run.toolsStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about middleBrick | API-Security
How do I install middleBrick | API-Security in Claude Code?
Run claude mcp add --transport http middlebrick-api-security https://api-security--middlebrick.run.tools. That registers the remote HTTP server as middlebrick-api-security.
What does middleBrick | API-Security do?
It scans an API for OWASP Top 10 style flaws and returns a risk score, keeping earlier runs available by id.
Which tools does it add?
Three: scan_api starts a scan, get_scan returns one earlier run, list_scans lists the scans you have already made.