"Google Cloud Composer" matching MCP servers:

MCP server for auditing infrastructure-as-code attack paths, finding multi-hop chains from public internet to sensitive resources.

This server enables AI-assisted APK reverse-engineering entirely on-device, orchestrating jadx, apktool, adb, frida, and APKiD through a job/workflow engine, and exposing those agents as native MCP tools for Claude without any cloud dependency.

Enables AI assistants to scan websites, public repositories, and OpenClaw/CLAW skills for security vulnerabilities, including local skill-package analysis before installation, cloud scans, and remediation guidance.

Enables MCP-native multi-agent security audits for Google Antigravity, orchestrating subagents for 0day research, static analysis, PoC verification, exploit chaining, reporting, and code remediation.

A comprehensive security testing MCP server providing 51 tools for penetration testing, network forensics, memory analysis, and vulnerability assessment. It enables automated security audits and technical investigations across web applications, cloud environments, and network captures.

Enables AI assistants and the WYRE Conduit gateway to access Telivy's security assessment data for MSPs, including external scans, deep-scan risk assessments, device inventory, M365/Google Workspace user exposure, PII summaries, and finding-level details.

An MCP server providing AI-powered cybersecurity, penetration testing, reconnaissance, vulnerability assessment, and security automation tools through the Model Context Protocol.

An MCP server that checks Composer, npm/pnpm/Yarn, and pip/Poetry/uv lockfiles against public security advisories, enabling a coding agent to report whether installed packages need patching and what to upgrade or remove.

Enables AI agents to query the Shodan API and CVEDB for internet-connected device reconnaissance, returning open ports, banners, TLS certificates, cloud and location details, plus DNS records and subdomains. Also delivers vulnerability intelligence such as CVSS, EPSS, and KEV status for CVEs, products, and CPEs.

Exposes nmap, httpx, ffuf, and sqlmap to AI agents over MCP with mandatory scope enforcement, blocked cloud metadata and private addresses, and shell-free command execution. Enables authorized port scanning, HTTP probing, content discovery, and SQL injection verification with validated arguments and auditable output.

Enables AI assistants to directly invoke Kali Linux network tools for network maintenance and security assessment, with 19 tools including port scanning, DNS queries, and penetration testing.

Enables AI assistants to drive OWASP ZAP through 67 curated, safety-gated tools for crawling targets, running authenticated spider and active scans, triaging alerts by severity, and exporting reports. Every attack-capable action is checked against a target-authorization policy that refuses cloud-metadata endpoints and out-of-scope hosts.

Enables AI assistants to query vulnerability management, security center, identity exposure, and cloud security data read-only, and to export Active Directory data from identity exposure into a BloodHound attack graph.

Enables AI coding assistants to run static analysis on GitHub repositories, raw code snippets, or local directories to detect cloud cost leaks in Terraform/AWS configs, PostgreSQL migration table-lock hazards, and OWASP/Next.js API security gaps. Each finding returns structured severity, line-level detail, and drop-in fixes.

Enables AI agents to scan a repository or project for malware, supply-chain attacks, leaked secrets, and web, server, cloud, and CI/CD vulnerabilities, then confirm real findings with concrete attack scenarios and fixes. Exposes scan, guide, and reference tools plus a security-review prompt that runs locally.

Enables MCP-compatible agent hosts to delegate governed, read-only security audits and reviews of code, applications, agents, prompts, MCP configurations, and cloud environments through evidence-first findings and stable schemas.

AI-powered cybersecurity automation platform with 155+ security tools for network, web, cloud, and binary analysis, controllable via natural language through MCP-compatible AI assistants.

An MCP server that extends kali-mcp with cloud (AWS/Azure/GCP), API/GraphQL/JWT, OSINT, container/K8s, IaC/SAST, mobile, binary analysis, and reporting tools, all accessible via an HTTP MCP endpoint.

Enables auditors to scan cloud IAM policies for privilege-escalation paths, wildcards, and risky grants directly within Cursor or Claude Code, using a deterministic rule engine that runs entirely on local infrastructure.

Enables AI to scan AWS accounts, analyze attack paths, and verify security fixes on a read-only graph of cloud resources.

Enables AI agents to query the Shodan API and Shodan CVEDB for internet-connected device search, host reconnaissance (open ports, banners, TLS certificates, cloud provider), domain and DNS lookups, and vulnerability intelligence with CVSS, EPSS and KEV data. Supports both stdio and HTTP streaming transports, with credit-aware free tools for counting queries and CVE research.

Gives AI agents read-only access to the Shodan API and Shodan CVEDB, letting them look up open ports, banners, TLS certificates, cloud and location details for IPs, run paged device searches with facet breakdowns, resolve domains and DNS records, and pull CVSS, EPSS and KEV data for CVEs and CPEs. Supports stdio for desktop clients and HTTP streaming for shared deployments, with credit-aware free tools and zod-validated inputs.

Enables MCP clients to exercise HTTP tools against an upstream service, secured via bearer-token authentication, along with a resource and prompts.

Enables Claude or any MCP-compatible client to execute cybersecurity workflows like incident response, cloud audits, and pentests by calling tools with 323 prompts across 8 categories.

Provides 180+ tools for full system control including terminal, Git, Docker, Kubernetes, VMs, BIOS, kernel, cybersecurity, AI, and cloud, designed to work with MCP clients like Cursor and Claude Desktop.

MCP server (Python, official MCP SDK, stdio) in the mcp/ folder: tools scan_tls and scan_tls_raw check whether a website negotiates post-quantum TLS (X25519MLKEM768 / ML-KEM) and report the key-exchange group, certificate and grade.

MLNops is a local-first MCP server for authorized infrastructure reconnaissance and security posture analysis. It provides DNS, WHOIS, SSL/TLS, subdomain, ASN, cloud exposure, and full-recon tools for MCP clients.