Security

Security tools for your AI: scan, pentest, check headers, guard code and scan repos for secrets.

The rule engine behind the mcpready CLI: probe an MCP server over stdio or Streamable HTTP and build a graded, spec-cited readiness report.

Browser SDK for MCP authorization callbacks.

Burp Suite MCP server with 80+ tools for authorized web security testing

Catch every time your AI coding agent touches auth, secrets, or skips a test, then turn the correction you made into a local regression eval. Local-first, deterministic, no LLM judge.

Model Context Protocol server for TOTP verification codes on macOS, backed by the login keychain

密码管理器 MCP 服务器 — 为 AI 助手提供凭据管理、文件夹管理、密码生成等能力

A connected MCP server can still exfiltrate if the model asks — registerNomineeTool checks allow/ask/deny before the handler runs.

Act for a person on websites: sandboxed browser, phone approvals, saved logins, scheduled plans.

Protect an MCP server with Authio: token verification, protected resource metadata, WWW-Authenticate challenges and connected-account token exchange.

Bolvrk CLI — the deterministic checker for code. Verifies database migrations (Postgres; SQLite and SurrealDB in beta) and scans for committed credentials; runs as a CLI and an MCP server. Free rules run locally; the full corpus runs in the hosted service

Detect any website's tech stack, security headers, SSL, DNS and CVEs via DetectZeStack.

BCS fork of GitLab MCP server for pipelines, repositories, merge requests, issues, and content masking

Manage multiple Webflow MCP server connections (one per client/org) without ever letting an API token pass through agent context.

Dual-rail Lightning paywall for MCP servers: accepts L402 and x402 bip122/exact, one LNBits backend.

Extract user identity (name, emails, accounts, addresses, payments) from browser data into a self-ranking SQLite database. Install as a Claude Code agent skill.

MCP Security Lab — MCP Verifier: evidence-first, deterministic security checks for local and remote Model Context Protocol servers, with optional Claude-powered remediation.

A security scanner and linter for Model Context Protocol (MCP) servers. Like npm audit / eslint, but for MCP.

Security scanner for AI agent tools. Local static scan of MCP IDE configs (41 rules, toxic flow heuristics, AAuth visibility, auto-fix, tool pinning). Optional proxy + in-browser dashboard: traffic, findings, AAuth Explorer, YARA, Playground. Smart Scan o

Townhouse CLI, MCP server and SDKs: scan your app from any editor, agent or terminal, get proven fixes, track errors in the browser, Next.js, Node, Deno and edge runtimes, upload source maps, and meter provider calls