MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
CyberMCP is a Model Context Protocol (MCP) server designed for testing backend APIs for security vulnerabilities. It provides a set of specialized tools and resources that can be used by LLMs to identify common security issues in APIs.
MIT ★ 16 -
invguardgithub.com/xordej/invguardupdated this year
Self-hosted vulnerability watchdog for the hardware and software you actually own. Manual inventory only — no network scanning, by design. Tracks NVD, CVE List V5, OSV, KEV, EPSS, Cisco PSIRT, MSRC and CSAF vendors, matches them against your CPEs and PURLs, and reports only what affects you. One container, SQLite, MCP server included.
★ 1 -
Vulnerable-by-design MCP server for learning object-level / cross-tenant authorization (BOLA/IDOR) bugs, plus Semgrep rules that find the same shapes in JavaScript/TypeScript, Python, Go, Rust, Java, Kotlin, C#, PHP, Ruby and Swift MCP servers - shipped as a GitHub Action with SARIF output.
MIT -
playgroundgithub.com/mcpscanner/playgroundupdated this year
Public, intentionally-vulnerable + hardened demo MCP server for testing mcpscanner. /error (Grade F), /success (Grade A), /random.
Apache-2.0 -
trust-boundary-ctfgithub.com/acseguin21/trust-boundary-ctfupdated this year
Browser-based MCP CTF — OAuth token confusion and session isolation failure (CVE-2025-49596 pattern). DevTools only.
MIT -
FYP-XploitEye-Web-and-System-Vulnerabilities-using-Agents-LLMs-github.com/shoaib1522/FYP-XploitEye-Web-and-System-Vulnerabilities-using-Agents-LLMs-updated this year
XploitEye is a state-of-the-art, AI-powered multi-agent cybersecurity platform designed to automate the complete Cyber Kill Chain. By orchestrating advanced Large Language Models (LLMs) and industry-standard security tools, XploitEye provides a unified interface for both Red Team (Offensive) and Blue Team (Defensive) operations.
-
MCP server for VulnWatch — query scans, status and reports from Claude Code, Cursor and Codex. Read-mostly by design.
MIT