A portable Agent Skill for defensive software design, implementation, review, and verification. It routes agents to focused guidance for the trust boundaries that actually change, from a bounded fix to an architecture review or staged brownfield rollout.
Enables authorized web/API security analysis as a stateful, multi-stage workflow with persistent session state, human-controlled validation, candidate versus confirmed finding tracking, and stop conditions.
Exposes an Auth0 Form as an MCP server, enabling AI models to interact with the form via natural language. It uses a stateless HTTP MCP transport with Auth0 authentication.
Enables autonomous agents and MCP-compatible clients to enforce policy-approved actions using risk tiers, reversible checkpoints, and token approval bounds.
Provides investigation tools for Cloudflare CCF data in Microsoft Sentinel, enabling security posture assessment, threat detection, and IP reputation analysis through customizable MCP tools.
An MCP authorization server implementing OAuth2/OIDC flows, supporting dynamic client registration, PKCE, consent screens, and client ID metadata documents for MCP authorization.
Enables control and monitoring of an ADT Control / Alarm.com security system from MCP-compatible hosts, including checking system and device state, reviewing activity, and safely arming, disarming, locking, or adjusting devices through confirmation-gated actions and a local audit trail.
A local MCP server that provides a safe plan-and-execute workflow for AI coding assistants, storing plans and tasks, and executing agent commands with an allow-list for security.
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.
Authentik MCP provides seamless integration with Authentik's API, supporting both full-featured and diagnostic modes. These enable secure, automated user, group, and system management through MCP-compatible tools.
Enables AI assistants to perform penetration testing and security assessments by exposing 60+ Kali Linux security tools including network scanning, web security testing, password cracking, exploitation frameworks, and OSINT capabilities through an AI-friendly interface.
Enables auditing and monitoring of AI agent MCP tool calls, with behavioral anomaly detection, lab-scoped red-team simulation, and Telegram notifications.
Exposes 106 ManageEngine Endpoint Central REST API endpoints as MCP tools for patch management, vulnerability management, inventory, and more, integrated with Gemini Enterprise via Zoho OAuth 2.0.
Drop-in stdio interceptor that gates MCP tools/call requests through a YAML policy (block / require_approval / audit / budget cap) before they reach the real server. The same policy file is reused by @jamjet/claude-code-hook and @jamjet/openai-guardrail, so one rule set covers Claude Desktop, Cursor, OpenAI Agents, and custom clients.
MCP server for creating and managing SOPS-encrypted secret files using age encryption, enabling AI agents to generate and manage secrets without ever seeing plaintext values.
Enables AI agents and MCP clients to perform read-only SQL Server DBA investigations across health, performance, backups, jobs, security, and schema design. It allows the AI to suggest fixes, but SQL Server permissions and tool checks prevent any database changes.
Enables email alias management through the upstream REST API, including listing, creating, updating, toggling, and deleting aliases, plus mailbox discovery and account validation. API credentials are retrieved from 1Password at launch and kept only in the server subprocess environment.
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.
Manage AWS, Hetzner, OVH, and custom SSH servers from AI agents — commands, logs, CloudWatch/CloudTrail, IP banning, and S3, with guard tiers and a full audit trail.
An MCP server that provides a comprehensive interface to Semgrep, enabling users to scan code for security vulnerabilities, create custom rules, and analyze scan results through the Model Context Protocol.
Enables Claude Desktop and custom AI agents to securely access enterprise Postgres databases and Notion knowledge bases via MCP, with read-only SQL enforcement, audit logging, and API-key authentication.
Exposes the 1E Platform Consumer API as 92 callable MCP tools, enabling MCP-compatible LLM clients to manage devices, instructions, approvals, users, groups, custom properties, and other resources across a 1E DEX tenant.
Enables AI agents to interact with the ComplianceCow platform to retrieve compliance insights, dashboard data, and auditable evidence through a Compliance Graph. It also supports automated remediation actions such as fixing policies and creating tickets in external tools.
Enables sanitizing and masking personal data, trade secrets, and confidential information in PDF, Word, PowerPoint, and image documents through a remote MCP endpoint with zero installation, no API keys, and zero retention.
Enables MCP clients to safely connect to MCP servers by sanitizing sensitive data in tool results and restoring it in tool arguments, so the model never sees PII while downstream tools still receive real values.
A plugin-based MCP server that securely exposes custom tools to AI agents, keeping sensitive information hidden while enabling operations like email whitelisting through pluggable plugins.
An MCP server that enables AI agents to manage a TODO list with user authentication via Stytch. It provides tools for creating, reading, updating, and deleting TODO items while handling identity and authorization.
Enables Claude Desktop to redact and count personal data in PDFs and images, strip hidden metadata from photos, anonymize Word and text files, prepare watermarked ID copies, and compare contract versions using only user-approved local folders. All processing runs offline on the user's computer, creating new copies instead of modifying or deleting the originals.
Enables connecting Postgres databases to MCP clients with built-in query and inspection tools, custom parametrized SQL tools, scoped API keys, group permissions, and audit logging.
Enables AI agents to build disclosure requests and validate passport, statement, request, and proof-envelope documents, including structural checks of received presentations for audience/nonce binding, expiry, and requirement coverage. It is local and read-only, and currently never accepts presentations because real proof verification and registry support are not yet implemented.
Enables AI assistants to manage PocketBase databases by creating and inspecting collections, performing record CRUD with filters and pagination, authenticating and managing users, and backing up databases through the Model Context Protocol.
Enables network security scanning using Nmap through MCP protocol. Supports quick port scans, full port scans with service detection, and custom Nmap commands with async task management.
Enables AI agents to securely perform privileged actions like creating GitHub issues by minting short-lived, single-purpose tokens on demand, with policy enforcement and audit logging.
MCP server for managing Defined Networking infrastructure through API tools. It enables network administration including host management, firewall rules, tags, and network configuration with Claude Code integration for interactive network design and auditing.
Enables smart contract security auditing using Slither, Aderyn, and custom pattern analysis through the Model Context Protocol, allowing AI assistants to run static analysis and vulnerability checks on Solidity and Vyper contracts.
Enables AI agents to manage GPMLogin browser profiles over the GPM Local API — health checks, listing and searching profiles, creating profiles with proxy aliases, renaming, starting and stopping, and approval-gated deletion. It supports both gpm-v3 and global-v1 API flavors, stores proxy credentials in Windows Credential Manager, and defaults to read-only mode so writes and deletes must be explicitly enabled and approved.
Enables auditing of npm, Yarn, and pnpm lockfiles in local project directories or remote Git repositories for known vulnerabilities, with configurable severity thresholds, dev-dependency skipping, custom registries, and text or JSON reports.
Description:
Introduce Beelzebub, an MCP‑based honeypot framework that enables creating decoy tools to detect prompt injection and malicious agent behavior.
Motivation:
Strengthen the security of LLM workflows by adding a non‑intrusive detection mechanism.
Enables users to manage self-sovereign identity credentials by creating schemas, issuing verifiable credentials, generating verification QR codes, and checking verification status via the Empe SSI ecosystem.
Audits npm, Yarn, and pnpm lockfiles from a local project directory or a remote Git repository, exposing a package_audit tool that returns vulnerability results with configurable severity thresholds, custom registry, dev-dependency skipping, retries, and JSON or text output in Chinese or English.
Enables irreversible anonymisation of documents and spreadsheets (PDF, Word, PowerPoint, HTML, Excel, CSV) into consistent pseudonymised Markdown before they reach an AI, keeping names, national IDs, bank details and contact data unrecoverable. Runs as a free online HTTP endpoint needing no key, or locally with the full engine bundled so nothing leaves the machine.
Runs a single self-hosted service that exposes multiple plugin-scoped MCP endpoints, so users can add each plugin as a custom connector and manage installation, loading, and access controls from an admin UI while keeping data local.
Provides governed tools for evaluating proposed agent actions against policy, classifying risk, and creating structured governance and audit records, while pausing consequential steps for explicit human approval. This lets agentic workflows run under traceable, least-privilege control rather than unrestricted automation.
Offline, read-only MCP server that predicts which custom Wazuh rules wazuh-analysisd will ignore at load (missing or later-loaded if_sid, if_group, duplicates, static fields) — calibrated 15/15 against Wazuh 4.14.7. Also lists Wazuh 5.0 migration blockers.
Enables existing websites to expose their features to Claude, ChatGPT, and custom AI agents over MCP, with OAuth consent, scoped permissions, user-set limits, and an audit log.
Enables AI agents to manage temporary password-gated public tunnels on Windows, including creating, starting, stopping, updating, and deleting tunnels, setting passwords, and checking for updates.
Enables MCP clients to access a CRM over stdio, with Microsoft Entra device-code sign-in so queries run as the signed-in user, and tools to start/check login and search CRM accounts.
Enables an AI agent to inspect and manage an XCA key and certificate database through its CLI, including listing items, generating keys, importing objects, creating CRLs, and optionally revoking certificates or signing CSRs with a patched XCA build.