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.
-
Self-contained Mobile & IoT SAST/DAST/pentest toolkit: MobSF + Frida + objection + mitmproxy + rooted emulator, as a desktop app, CLI and MCP server.
GPL-3.0 ★ 3 -
bad-mcpgithub.com/canack/bad-mcpupdated this year
10 intentionally malicious MCP servers that exploit protocol features to attack AI clients. For security research and defense testing.
MIT ★ 9 -
Zero-trust AI security research engine built on MCP, Tauri v2, and Rust — with prompt injection defense and sandboxed tool execution
MIT ★ 5 -
secure-rag-multi-agentgithub.com/ssdeanx/secure-rag-multi-agentupdated this year
Secure Retrieval-Augmented Generation (RAG) with role-based access control using Mastra AI orchestration, with JWT Secure, also Deep Research built with Cedar & Next.js. Gemini, OpenAI, Openrouter, & Gemini CLI usable. Also exposes tools, agents as MCP Server Also A2A Agent Cards
NOASSERTION ★ 19 -
MCP-powered offensive security intelligence engine using local semantic retrieval, FAISS, and RAG. Local-first MCP server for authorized offensive security research, detection engineering, and education. Authorized use only.
-
Security research PoC: console entry point for the unclaimed PyPI name used by CrowdSentinels-AI-MCP docs
pypi -
Security-first Binance MCP. 26 tools, human-confirmed spot trades, offline quant research.
pypi -
Ghidra-MCP-WSL-Autogithub.com/astroicers/Ghidra-MCP-WSL-Autoupdated this year
One-click deployment of Ghidra + GhidraMCP (Model Context Protocol) on WSL2 — AI-assisted reverse engineering for security researchers
★ 1 -
Next-generation AI/LLM-native proxy for authorized security research: proxy gateway, pool manager, session proxy with capture, multi-IP edge proxy and MCP control. Rust. https://proxyx.dev/
AGPL-3.0 ★ 1 -
cognitive-kitgithub.com/gabobase/cognitive-kitupdated this year
Pluggable cognitive layer — port of GCS v15.3 as an embeddable MCP cognitive kit. Provides reasoning, research, planning, creativity, reflection, security, knowledge, analysis, agency orchestration, and adaptive pipelines via MCP protocol.
npm MIT -
@iochus/aip-mcpgithub.com/ener-os/aip-protocolupdated this year
Agent Intelligence Protocol — Universal real-time intelligence for AI agents. Tech trends, security alerts, market data, DeFi yields, research papers, service status, developer tools, content signals, and more. 10+ domains. Free tier: 100 signals/day.
npm MIT -
MCP server for LeakIX API - security research and reconnaissance
MIT ★ 3 -
prompt-injection-mcpgithub.com/Xiangyu-Li97/prompt-injection-mcpupdated this year
MCP Server for authorized AI security research and penetration testing (Educational purposes only - requires explicit authorization)
NOASSERTION ★ 3 -
mcp-security-atlasgithub.com/Avinash333-D/mcp-security-atlasupdated this year
An advanced MCP server integrating industry-standard security tools (Nmap, ZAP, Metasploit, Burp) for automated vulnerability research and reconnaissance. Designed for ethical hackers and bug bounty hunters to streamline the 'recon-to-report' workflow via a unified LLM interface.
Apache-2.0 -
Token-optimized research engine & Agent Skill for 100% Open Access academic cybersecurity research (USENIX, NDSS, IACR, arXiv cs.CR, and NIST). Built for AI Agents & Security Analysts.
MIT -
tubemind-secure-mcpgithub.com/dewtech-technologies/tubemind-secure-mcpupdated this year
Secure MCP server for YouTube intelligence — 18 tools (search, analytics, benchmark, heuristics, competitor research) for Claude Desktop. OAuth2 + AES-256-GCM + OWASP Top 10.
npm MIT -
fuzzmind-frida-mcpgithub.com/0xca1x/frida-mcpupdated this year
Frida MCP server for authorized dynamic analysis and application security research
pypi MIT -
Open-source web security research workbench for macOS: intercept, discover, investigate, experiment, validate. CLI, local API and built-in MCP for AI agents.
Apache-2.0 ★ 5 -
Deep Research Serverno update data
Perform comprehensive web research by combining AI-powered search and deep content crawling to gather extensive, up-to-date information on any topic. Aggregate and structure research data into detailed JSON outputs optimized for generating high-quality markdown documentation with LLMs. Customize documentation prompts and output paths to fit your workflow and save research results securely.
smithery -
korean-keyword-mcpgithub.com/Whitening-Sinabro/korean-keyword-mcpupdated this year
Korean keyword research MCP server for Naver SearchAd/DataLab; Project Shield local security-scan notice pinned.
npm MIT -
A security-first MCP server that empowers AI agents to perform automated reverse engineering, malware analysis, forensics, vulnerability research, and SAST — powered by Radare2, YARA, LIEF, Capstone, and more.
go MIT ★ 222 -
Stream-first CAN & J1939 toolkit for security research and AI agents — typed JSONL events, CLI, TUI, fuzzing, MCP server.
pypi GPL-3.0 ★ 5 -
RedVector AI - AI-powered penetration testing and cybersecurity automation framework for security researchers and ethical hackers.
NOASSERTION ★ 47 -
Myceliumgithub.com/ItsNishi/Myceliumupdated this year
Structured, typed, cross-platform access to kernel-level OS information via MCP -- built for AI agents, security research, and reverse engineering
MIT -
BSides Ballarat 2026 - Security Research Assistant: A "Security Operations Center" inside VS Code demonstrating Model Context Protocol (MCP) for discovering, viewing, and visualizing academic vulnerabilities. Presented by Tim Haintz.
-
Aragorngithub.com/alfarom256/Aragornupdated this year
Direct DbgEng COM kernel debugger MCP server for Windows VM security research
WTFPL ★ 3 -
findmy-mcpgithub.com/cbxss/findmy-mcpupdated this year
Fast, concurrent MCP server discovery and analysis tool for security research
MIT -
intigriti-mcpgithub.com/alpernae/intigriti-mcpupdated this year
A Model Context Protocol (MCP) server for interacting with the Intigriti bug bounty platform's Researcher API. This enables AI assistants like Claude to help security researchers manage their bug bounty programs, submissions, and research workflow.
MIT ★ 4 -
PoC benign MCP server for update-hijack security research
npm -
Lite Model Context Protocol server for comprehensive CVE intelligence gathering with multi-source exploit discovery, designed for security professionals and cybersecurity researchers - Alpha Release
npm MIT -
@autom8minds/seo-mcpgithub.com/autom8minds/seo-mcpupdated this year
MCP server with 25 SEO tools: page analysis, site crawling, security auditing, Core Web Vitals, schema validation, keyword research, backlinks, and more.
npm MIT -
AI-Powered Offensive Security Research Engine - desktop-native security testing platform with native MCP integration. 90 tools, MITM proxy, stealth browser, autonomous AI agent. Built on Tauri + Rust + React.
MIT ★ 52 -
AI-powered MCP server for authorized WAF bypass testing and adaptive security research.
MIT ★ 1 -
PoC: Open Registry supply chain — unvetted server listing (security research)
npm -
A lightweight, extensible cybersecurity toolkit that connects AI assistants to security tools through the Model Context Protocol (MCP), enabling AI-assisted security research, scanning, and analysis.
MIT ★ 13 -
AISRF, the AI Security & Research Framework: every LLM request from your apps and agents becomes a ticket a human approves before it reaches the backend. Analyzers, guardrails (Rebuff, LLM Guard, NeMo, Lakera), red teaming (garak, promptfoo, PyRIT), source code review, reports, MCP server.
Apache-2.0 ★ 2 -
Public home of extenshi.io — cross-store catalog of 373k+ browser extensions with security analysis, plus developer tools (@extenshi/cli, @extenshi/mcp, @extenshi/guard) and CC BY 4.0 research reports
npm NOASSERTION ★ 1 -
Google Cloud Healthcare API Serverno update data
Provide healthcare data access and querying capabilities by integrating with Google Cloud Healthcare FHIR APIs and public medical research databases. Enable seamless retrieval of patient records, clinical data, and research articles through a secure and authenticated MCP interface. Enhance healthcare applications with real-time clinical insights and research information.
smithery -
VulneraMCPgithub.com/telmon95/VulneraMCPupdated this year
An AI-Powered Bug Bounty Hunting Platform - Comprehensive MCP server for security testing, vulnerability research, and bug bounty hunting
MIT ★ 51 -
browser-mcpgithub.com/zzzhhhaaannnggg6/browser-mcpupdated this year
Vibe-coded browser-automation MCP server. Lets an LLM read, search, and traverse a private knowledge base via a persistent browser session — no vendor API key. Personal study project; the security questions surfaced while building it are turning into my undergraduate research interest.
-
general-coding-tools-mcpupdated this year
MCP server with coding skills and subagents — debugging, code audits (correctness, security, best practices, SQL migrations), feature planning, testing (React/Vitest, Deno, pgTAP), UI/accessibility audits, deep research, and doc generation. Works with Cur
npm MIT -
Security-oriented Python tooling and CLI/MCP experiments for defensive research and developer workflows.
-
bubble-ai-backendgithub.com/Aadhavan-Pachauri/bubble-ai-backendupdated this year
Enterprise MCP Server for Bubble AI with secured LLM proxy, web search, code execution, and deep research streaming
-
AcademicHub-educhaingithub.com/mannubaveja007/AcademicHub-educhainupdated this year
Academic Hub A professional network for researchers to publish, collaborate, and monetize their work. Powered by Google's Gemini LLM with MCP context server for intelligent research assistance, and integrated with the OCID Edu Chain ecosystem for secure identity management.
★ 2 -
hexstrike-aigithub.com/0x4m4/hexstrike-aiupdated this year
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.
MIT ★ 13,615 -
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.
★ 1 -
Free MCP session-security audit as an MCP server — re-verifiable verdicts. Part of the Session-as-Identity research line.
MIT -
Owner-only, OpenAI-first hibernating Nous Hermes research agent with durable Sites state, Secure MCP Tunnel transport, disposable ChatGPT Work compute, native web research, and tool-less Codex OAuth inference.
MIT ★ 1 -
KaliMCP — Automate Kali Linux pentesting with MCP. Programmatic access to 25+ tools, SSH/reverse shell management, Docker test mode. For CTFs, security research, and automated reporting.
MIT -
@yantrixai/mcpgithub.com/yantrix-ai/yantrix-mcpupdated this year
Dynamic MCP server for the Yantrix API portfolio — 30+ tools across research, memory, language, legal, security, intelligence, and more.
npm MIT -
@praveen030686/yantrix-mcpgithub.com/praveen030686/yantrix-mcpupdated this year
Dynamic MCP server for the Yantrix API portfolio — 30+ tools across research, memory, language, legal, security, intelligence, and more.
npm MIT -
PriceWatchgithub.com/rhranov/PriceWatchupdated this year
Agentic AI price-research dashboard with MCP-ready workflows, secure scraping, price history, and real-time monitoring.
MIT -
rev-calc-mcpgithub.com/hoho087/rev-calc-mcpupdated this year
MCP tools for AI-assisted reverse engineering, binary analysis, exploit development, and security research calculations.
MIT ★ 1 -
MCP server Python project consisting of general tools with varying levels of access and agency: query APIs, manage a SQLite db, and network operations for network and security research.
-
MCP server that gives AI assistants binary analysis capabilities: static analysis via Ghidra, user-mode debugging via x64dbg, kernel debugging via WinDbg, and .NET decompilation via ILSpyCmd. Built for security research, malware analysis, and reverse engineering.
Apache-2.0 ★ 12 -
12-in-1 Autonomous B2A Intelligence Supermarket (x402 v2 Base USDC & MCP Server): DeFi Alpha, Whale Profiler, Prediction Markets, Security Audit, Leads & Research
MIT -
Give Claude, Cursor or any MCP client 40 public-data tools on Apify: research, public funding, leads, web security.
pypi MIT -
在 Android 手机上独立运行的 AI 工作台:内置 Debian ARM64 终端、可观察浏览器、MCP 与 App 操控,面向编程、安全研究与逆向分析,支持多模型协作。源码开放,安装包尚未发布。An on-device AI workspace for coding, security research and reverse engineering.
GPL-3.0 ★ 5 -
openresearch-mcpgithub.com/olanokhin/openresearch-mcpupdated this year
Zero-auth, security-hardened cross-domain research MCP server: web, academic, GitHub, news, weather, macro/finance, SEC, biomedical, Bluesky, YouTube. SSRF and prompt-injection defenses.
pypi Apache-2.0 ★ 12 -
Agent-driven ML researcher in a secure, reproducible KVM lab: five standalone scientific-state MCP servers within per-user VMs with driver / trusted / hostile zone isolation
Apache-2.0 ★ 8