Connects Claude or Cursor to middleBrick's API security scanner through three tools: scan_api to check endpoints for vulnerabilities, get_scan to retrieve results, and list_scans to browse scan history. You pass in a URL and optional HTTP method, and it runs checks against OWASP Top 10, LLM-specific risks, and GraphQL vulnerabilities. Requires a middleBrick API key from their dashboard. Useful when you're reviewing API security during development or want to catch common vulnerabilities without leaving your editor. Scans run asynchronously, so you initiate one and poll for results.
MCP server for middleBrick API security scanning. Lets AI assistants (Claude, Cursor, etc.) scan APIs for vulnerabilities via tool calls.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"middlebrick": {
"command": "npx",
"args": ["-y", "@middlebrick/mcp-server"],
"env": {
"MIDDLEBRICK_API_KEY": "mb_your_key_here"
}
}
}
}
Add to .cursor/mcp.json:
{
"mcpServers": {
"middlebrick": {
"command": "npx",
"args": ["-y", "@middlebrick/mcp-server"],
"env": {
"MIDDLEBRICK_API_KEY": "mb_your_key_here"
}
}
}
}
Get your API key at: middlebrick.com/dashboard
| Tool | Description |
|---|---|
scan_api | Scan an API endpoint for security vulnerabilities |
get_scan | Get results of a previous scan |
list_scans | List previous scans |
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | Yes | API endpoint URL |
method | string | No | HTTP method (default: GET) |
| Parameter | Type | Required | Description |
|---|---|---|---|
scanId | string | Yes | Scan ID to retrieve |
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | No | Max results |
offset | number | No | Skip count |
status | string | No | Filter: queued, processing, completed, failed |
| Variable | Required | Description |
|---|---|---|
MIDDLEBRICK_API_KEY | Yes | API key |
MIDDLEBRICK_BASE_URL | No | API URL override |
Apache 2.0 — middleBrick
MIDDLEBRICK_API_KEY*secretYour middleBrick API key (get one at middlebrick.com)
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent