A secure MCP server that stores and retrieves API keys and credentials, featuring encrypted storage, masked retrieval, and AI-powered recommendation via MCP sampling.
Secure credential management for AI agents — encrypted storage, auto-refresh, and rate limiting via a single MCP call. Supports OpenAI, Anthropic, Stripe, GitHub, Brave Search, Kalshi, Coinbase, plus generic API key and OAuth2 for any service.
Automates Android app analysis using Frida via AI commands, connecting a rooted Android phone to a computer and running dynamic analysis scripts without manual command execution.
Enables forensic investigators to acquire data from Android devices via ADB, including device backup, artifact collection, and secure command execution.
Enables multi-dimensional architecture review of technical solutions with web intelligence and knowledge base auto-sedimentation, acting as a logical security gateway for Claude Code.
An MCP server that enables AI assistants to analyze Android APK and iOS IPA files for security issues through natural language conversation, including permission auditing, secret detection, and SDK enumeration.
An AI-driven Android dynamic analysis tool that enables AI models to perform automated reverse engineering by controlling Frida. It provides capabilities to inject scripts, manage application processes, and analyze real-time execution data through the Model Context Protocol.
Exposes internal databases, HTTP APIs, and files to LLM agents over MCP, with auto-generated schemas, access controls, rate limiting, redaction, and audit logging.
Enables agents to search and call the full OPNsense core and plugin API, perform model-validated CRUD and settings operations, and use curated firewall, service, and network tools with optional auto-revert writes.
Inspect captured HTTP/HTTPS traffic through MCP to analyze APIs, authentication and pagination with request-level evidence. Free, MIT-licensed desktop app for macOS and Windows with Android USB capture.
Enables MCP-compatible AI clients to analyze Android APK and iOS IPA files for security issues through natural language, including permission auditing, API endpoint extraction, hardcoded secret detection, Firebase inspection, and third-party SDK enumeration.
MCP server that bridges authenticated sessions from a Chrome extension to CloakBrowser profiles via local WebSocket, enabling agents to sync, verify, and debug persistent login state without exposing raw credentials.
Provides access to Better Auth framework documentation, authentication provider configurations, database adapter setup, and generates production-ready authentication configs for modern web frameworks.
Enables testing API authentication and authorization by probing endpoints with and without Authorization headers, suggesting auth test matrices for roles, and showing current test configuration.
Provides real-time policy enforcement for AI coding agents by intercepting and validating their actions against organizational standards like naming conventions, security policies, and compliance rules before execution. Prevents violations through immediate feedback and auto-correction suggestions.
An MCP server that enables AI-assisted mobile security testing by exposing Frida functionality for Android application research. It provides tools for hooking Java methods, manipulating memory, managing device processes, and executing custom Frida scripts.
Enables provisioning and management of IPsec tunnels and BGP-over-IPsec peers on Palo Alto Panorama-managed firewalls, with candidate-only, human-committed workflows and additional read/write tools for PAN-OS operations.
Enables local-first static and optional controlled dynamic analysis of Android APK artifacts, with provenance-aware downloads, Markdown reports, and structured security findings via MCP stdio tools.
Enables developers and security teams to run evidence-first Android and iOS security audits, manage jobs and reports, query public vulnerability intelligence, evaluate policies, and plan runtime checks through stdio MCP tools and resources.
MCP server for secure credential management, browser-based login automation, and TOTP/2FA auto-solving. Encrypts credentials with AES-256-GCM and automates login flows via Playwright.
Enables enterprise-grade authentication management with secure credential handling and support for multi-protocol auth, complete with tools for analyzing, setting up, and testing authentication systems.
Enables secure file delivery by encrypting files client-side and generating one-time, auto-deleting download links, with tools to create sends, check their status, and revoke them.
Enables AI assistants to operate Juniper Junos and SRX network devices over NETCONF and SCP, running operational CLI and PFE commands, inspecting and diffing configuration, validating and committing changes with confirmed auto-rollback, and managing SRX security workflows such as signature-package updates, chassis-cluster health, and read-only policy and address-book inspection.
Control-plane proxy that sits in front of MCP servers, enforcing per-identity policy (YAML/OPA/Cedar), budget limits, and an audit trail on every call. Includes real-time anomaly detection that auto-blocks a compromised agent without a human in the loop.
Bridges any stdio-based local MCP agent to Figma's remote MCP server, letting agents access Figma's tools after a single browser authorization that is stored locally and auto-refreshed. It works around Figma's OAuth client allowlist and requires no OAuth support on the agent side.
Authentication and authorization plugin for appium-mcp, adding bearer API keys, OAuth JWT, session tokens, scope-based authorization, rate limiting, and per-session ownership when running over SSE/HTTP Stream.
Enables importing and auto-analyzing binaries with Ghidra's headless analyzer, then listing, decompiling, disassembling, cross-referencing, searching, and annotating them — individually or across a whole project — without requiring a running GUI or bridge plugin.
Enables AI agents to scan GitHub repositories for security vulnerabilities, deployment blockers, and code quality issues. It provides detailed findings and auto-generated code patches to help developers ensure their code is production-ready.
A Nostr-based authentication gate for MCP servers that requires agents to sign HTTP requests with a Nostr key, verifying signatures offline to secure tool access.
Local static-analysis assistant for Android malware research that manages investigation cases, exposes MCP tools via a local server, and persists evidence-backed findings without cloud dependency.
Ntfyx plugin 0.2.0 sends agent questions and updates to iPhone, Android and a phone-authorized Web Inbox. Local stdio MCP requires the signed CLI (current 0.1.6; minimum 0.1.3+), phone pairing and Ntfyx's hosted relay; not a standalone cloud server. Apple silicon native approvals are verified with CLI 0.1.5+; Intel Mac is unverified. MIT covers only plugin adapters.
Enables AI agents to read and manage Microsoft 365 multi-tenant environments through the CIPP API, covering tenants, users, groups, mailboxes, conditional access, standards, licenses, and GDAP data. On explicit request, it can perform write actions such as creating or editing users, resetting passwords, offboarding leavers, configuring auto-replies and forwarding, and running standards.
A FastMCP server template with full MCP authentication via Descope, designed for easy deployment on Render. It provides a foundation for building secure, authenticated MCP servers with scope-based access control.
Enables AI clients to connect to remote OAuth 2.0-protected MCP servers through a zero-config stdio-to-Streamable HTTP bridge with automatic discovery, PKCE login, and silent token refresh.
Enables AI coding agents to dynamically inspect running software — API hooks, syscall summaries, memory inspection, and HTTP/TLS/DNS reconstruction from live traffic or pcaps — across Linux, macOS, and Android targets. Every finding is returned as a structured Evidence Record with observation, artifacts, confidence, and explicit limitations, so agents cite proof rather than guess.
MCP server for Renef, providing dynamic instrumentation and reverse engineering capabilities for Android ARM64, including native hooking, Java interception, and memory manipulation.
Connects AI agents and MCP clients to Zendesk through an authenticated PipMCP gateway with hosted tool discovery and governed execution, enabling review of support tickets and creation of new tickets with customer-service comments. Calls run under workspace, role, policy and approval controls with idempotent receipts instead of auto-approved writes.
A remote MCP server implementation that demonstrates authentication and authorization capabilities using OAuth 2.1. This is a workshop project for learning how to build secure MCP servers with user authentication.
Enables MCP clients to scan codebases, persist and prioritize security findings against SLAs, retrieve CVE details, propose fixes, and create tickets through its tools. It also supports agent-assisted remediation drafting while enforcing human approval and preventing auto-merge.
Enables users to audit a domain's email-authentication DNS configuration—covering SPF, DKIM, DMARC, MX, BIMI, MTA-STS, and TLS-RPT—and receive issues, recommendations, a 0–100 score, and A–F grade.
Enables validating Microsoft Entra access tokens to determine whether an MCP caller is a signed-in user or only an application, illustrating MCP authentication methods.
Autonomously introspects an undocumented SQLite database to expose auto-generated CRUD tools, join-explaining prompts, and schema resources for LLM agents. All queries run through pre-validated parameterized SQL templates, so the model never writes or sees raw SQL, with full audit logging of every operation.
Connects AI agents and MCP clients to a hosted gateway where they can discover real tools, validate arguments against returned schemas, and execute governed file and folder operations in Dropbox using a single PipMCP API key. Workspace, role, policy and approval controls, plus idempotency receipts, keep every provider action reviewed rather than auto-approved.
A reusable template for building MCP servers that act as OAuth 2.1 resource servers, verifying bearer tokens against Microsoft Entra ID or any standards-compliant OIDC authorization server.
Fast, low-latency MCP server for authentication services, enabling AI agents like LM Studio and Claude Desktop to perform user authentication operations such as sign-in, sign-up, OTP verification, and token management.
Enables free Xero accounting access through MCP clients by handling one-time PKCE sign-in and refresh-token persistence, letting users run the official Xero MCP server without a paid Custom Connection.
Enables MCP access to multi-tenant PostgreSQL data where tenant isolation is enforced by row-level security instead of application-layer filters, removing the need for per-handler tenant checks and service-role keys on the request path.
A production-minded MCP server kit that provides OAuth 2.1/PKCE authentication, rate limiting, scope-gated tools, and two-phase confirmation for building secure MCP servers with custom tools, identity, and storage.