middleBrick runs on your own machine — the client starts it, so there is no endpoint to ping. 24 installs a week from npm. Last commit 3 Apr 2026.
Scan APIs for OWASP Top 10, LLM, and GraphQL security vulnerabilities.
Today is the operative word: we check middleBrick every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-server -- npx -y @middlebrick/mcp-server
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@middlebrick/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-server]
command = "npx"
args = ["-y", "@middlebrick/mcp-server"]
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@middlebrick/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@middlebrick/mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
MIDDLEBRICK_API_KEY (Your middleBrick API key (get one at middlebrick.com)).
The author declared them in the registry entry; get the values from the project itself.
Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.
Scan websites for security vulnerabilities, headers, TLS, and email security.
Scan a website for vulnerabilities: OWASP Top 10, CVEs, SSL, headers - with plain-English fixes
AI-Powered Security Scanner for LLMs. Detects vulnerabilities and syncs with SynapseAudit.
Analyzes code for bugs, security vulnerabilities, and code smells
FinishKit MCP: scan GitHub repos for security vulnerabilities, deployment blockers, and quality
Trigger security scans and read reports/vulnerabilities via the hosted Scannd API. Free: 2 scans/mo.
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
Answers built from our own checks of this server.