<strong>The security MCP server that turns your AI into a penetration tester.</strong>
Firebreak MCP server exists for a simple reason — assistants are far more useful when they can act on Firebreak directly instead of describing what you should do. The security MCP server that turns your AI into a penetration tester..
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Once Firebreak is connected, these are the calls the assistant has available:
firebreak_best_practice — Security best practices for a topicfirebreak_check_pattern — Scan code for insecure patternsfirebreak_explain_vuln — Explain a vulnerability typefirebreak_security_checklist — Generate a security checklistfirebreak_owasp_check — Map a finding to OWASP Top 10firebreak_analyze_rls — Analyze SQL for RLS policy issuesfirebreak_scan_quick — Fast scan, critical+high only (2-3 min)firebreak_scan_full — Full pen test (black/gray/white box)firebreak_scan_target — Focused scan on one areafirebreak_scan_status — Check progress of a running scanfirebreak_scan_stop — Stop a scan, keep partial resultsfirebreak_results — Scan summary with security score (A-F)You will need one environment variable: FIREBREAK_HOST. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Firebreak's toolset — firebreak_best_practice, firebreak_check_pattern, firebreak_explain_vuln and 11 more — is a fair guide to whether it matches your workflow. It is maintained by protonese3; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| firebreak_best_practice | Security best practices for a topic |
| firebreak_check_pattern | Scan code for insecure patterns |
| firebreak_explain_vuln | Explain a vulnerability type |
| firebreak_security_checklist | Generate a security checklist |
| firebreak_owasp_check | Map a finding to OWASP Top 10 |
| firebreak_analyze_rls | Analyze SQL for RLS policy issues |
| firebreak_scan_quick | Fast scan, critical+high only (2-3 min) |
| firebreak_scan_full | Full pen test (black/gray/white box) |
| firebreak_scan_target | Focused scan on one area |
| firebreak_scan_status | Check progress of a running scan |
| firebreak_scan_stop | Stop a scan, keep partial results |
| firebreak_results | Scan summary with security score (A-F) |
| firebreak_finding_detail | Full evidence for a specific finding |
| firebreak_finding_fix | Generate fix code for a finding |
{
"mcpServers": {
"firebreak": {
"url": "http://localhost:9090/mcp"
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| FIREBREAK_HOST | Endpoint or connection string the server talks to. | Optional |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.