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.
-
kali-defense-mcp-servergithub.com/bottobot/kali-defense-mcp-serverupdated this year
Ultimate Kali Defensive Security & System Hardening MCP Server — 78 defensive security tools for firewall management, CIS benchmarks, intrusion detection, malware scanning, container security, zero-trust networking, and more.
npm MIT -
MCP tools for CelesTrak satellite passes, NOAA space weather and NOTAM GeoJSON envelopes.
MIT ★ 1 -
convoyplangithub.com/cognis-digital/convoyplanupdated this year
Defense logistics route/sustainment planner computing fuel, resupply windows, and chokepoint risk from a YAML plan.
NOASSERTION -
wavewatchgithub.com/cognis-digital/wavewatchupdated this year
Offline RF signal reconnaissance & triage from capture files — detect, fingerprint & classify emitters (drone/Wi-Fi/BLE/GNSS) without demod. Defensive, zero-dependency, CLI + MCP.
NOASSERTION ★ 2 -
Secure read-only MCP server for typed job search, deterministic ranking, explainable matching, adversarial defenses, and audited tool use.
MIT -
fittin-mcpactive
Free startup protection and IP strategy MCP for Cursor and Claude builders — clone risk, defensibility, moat analysis
pypi MIT -
goop-shield-communitygithub.com/kobepaw/goop-shield-communityupdated this year
Runtime defense for AI agents. 24 inline defenses, 3 output scanners, MCP server, framework adapters.
Apache-2.0 ★ 2 -
Zero-waste, frugal token defense engine & native MCP server for AI coding agents — Token Bill Defense, Rate Limit Armor & Context Retention
pypi MIT -
🛡️ APHANIS :: Zero-Trust AI Provenance Firewall, Automatic Humanizer Engine & Stego Defense Platform
pypi MIT ★ 4 -
hal-web-mcpgithub.com/Halfax/hal-web-mcpupdated this year
Web search/fetch MCP server behind a real SSRF wall — DNS-rebinding defense, private-range blocking, 31 tests.
-
healthcare-credentialing-intelligence-mcpgithub.com/apifyforge/healthcare-credentialing-intelligence-mcpupdated this year
Healthcare provider credentialing is your first line of defense against fraud, exclusions, and liability.
MIT -
Treat normalized scan findings as immune signals: discover patterns, synthesize non-executing defenses, remember what worked.
MIT -
MCP server for Moodle with server-side prompt-injection defenses, SSO login and Obsidian vault sync
pypi MIT -
Hardware-anchored DeFi MCP server (defensive security tool). GSD-planned rebuild of vaultpilot-mcp.
NOASSERTION -
Industrial-grade defensive unit test synthesis Model Context Protocol (MCP) server for Cursor and Claude Desktop
MIT -
MCP server for Moodle with SSO login, server-side prompt-injection defenses and Obsidian sync
pypi MIT ★ 2 -
sqlguard-mcp:只读 SQL 防护 MCP 服务器。Read-only SQLite MCP server with layered SQL defenses for AI agents
MIT -
Real-time capital oversight, drawdown alerts, and news blackout defense for funded prop traders (MCP Server)
MIT -
@declaw/mcp-servergithub.com/declaw-ai/mcp-serverupdated this year
MCP server for Declaw — secure AI sandboxes with network policies, PII scanning, injection defense, and audit logging
npm Apache-2.0 -
Enterprise-grade Zero-Leak Secret Defense & Sandbox for Autonomous AI Coding Agents
npm Apache-2.0 -
Sentinel-ThreatWallgithub.com/ben854719/Sentinel-ThreatWallupdated this year
Sentinel‑ThreatWall integrates an advanced C++ firewall with AI-based anomaly detection, providing comprehensive real-time analysis, reliable telemetry, and responsive network defense.
Apache-2.0 ★ 1 -
Open source regime-adaptive financial analysis engine with MCP tool orchestration. Apache 2.0 licensed with defensive patent grant.
pypi Apache-2.0 ★ 5 -
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 -
Enterprise-Grade Zero-Leak Secret Defense & Sandbox for Autonomous AI Coding Agents (Claude Code, Cursor, Windsurf, Codex, Antigravity)
npm Apache-2.0 ★ 3 -
simply-ops-guardgithub.com/nardovibecoding/simply-ops-guardupdated this year
Claude Code plugin - 49 hooks + 28 MCP tools for enforcement, security scanning, prompt injection defense, VPS ops, audit logging
AGPL-3.0 ★ 1 -
acd-persona-generator-mcpgithub.com/agent-character-design/acd-persona-generator-mcpupdated this year
MCP server for ACD-compliant AI agent persona specs. Level 2 loop design, drift defense, behavioral memory. Not just system prompts.
npm MIT -
centinelagithub.com/amurlaniakea/centinelaupdated this year
A lightweight, defense-in-depth SecOps daemon for Linux/WSL that monitors processes and network traffic, provides plain-language threat explanations, and executes opt-in automated containment via an MCP agent bridge.
AGPL-3.0 ★ 1 -
Generate ACD-compliant AI agent persona specifications. Not just system prompts — complete character architectures with Level 2 loop design, drift defense, and behavioral memory.
npm MIT -
Stateless HTTP 402 micropayment gateway and pre-socket runtime defense engine for autonomous AI agents on Arc Layer 1.
pypi -
MCP fetch server with correct SSRF defense: resolve once, validate and pin the resolved IP, re-check every redirect. Returns clean markdown framed as untrusted data.
npm MIT ★ 1 -
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 -
Privacy-first Multimodal Data Refinery, Repo Context Firewall (Prompt Injection & Trojan Source Defense), Offline Vietnamese OCR, Multilingual E5 ONNX + SQLite FTS5 RAG & 9-Tool MCP Server.
MIT ★ 7 -
🥷 The AnonSec MCP Server enables anonymous email management via Firefox Relay with defense-in-depth PQC for data at rest.
MIT ★ 1 -
Find hidden prompt-injection text: ASCII smuggling, zero-width/emoji stego, bidi, homoglyphs. One layer, not a full defense: it does not judge prompt injection written in plain, visible words.
MIT -
Let your AI agent audit any website: image SEO, alt text fixes, domain DNS/SPF/DMARC and defensive exposure checks over one MCP URL. Claude, Cursor, Codex, VS Code, ChatGPT.
MIT -
Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial testing, and real-time threat detection.
pypi AGPL-3.0 ★ 21 -
美股进攻/防守四档信号系统:AI供需+货币/财政/行政四维数据驱动,公开Track Record,开放API/MCP · US stock attack/defense signal system: 4 data-driven dimensions, public track record, open API & MCP
★ 1 -
Saeroon unified MCP server — curated saeroon_* workflow tools (site backend capabilities, ContentType meta-CRUD, form/board/booking/members provisioning) + (A4) platform admin. stdio + Streamable HTTP + OAuth 2.1 + JWT ES256 + Rug Pull 3-defense.
npm MIT -
Defensive MCP server that detects website manipulation aimed at search engines and AI assistants: hidden prompt injection, AI recommendation poisoning links, sneaky redirects, hidden spam.
npm MIT -
The Zero-Trust Safety & Settlement Rail for Autonomous AI Agents. Sub-10ms deterministic guardrails, key leak defense, and cryptographic Proof-of-Safety attestations via x402 on Base ($0.002).
npm MIT ★ 3 -
Cross-vendor multi-model review committee that gates AI/agent-generated content before it ships — consensus-based hallucination defense. Zero dependencies, local-first CLI, MCP server, CI gate exit codes.
GPL-3.0 ★ 1 -
blagithub.com/qybaihe/blaactive
🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protecting JS/TS, Electron ASAR, WASM, Python, Native Binaries, SQLite, GGUF/Safetensors & Android DEX against AI reverse-engineering agents (REA).
npm MIT ★ 5,810 -
Pandaone Guard — Free open-source MCP server for AI code audit. L1-L6 defense (file lock + audit log + pre-commit hooks) for Claude/Cursor/Trae. Local stdio, no API key, MIT.
MIT ★ 1 -
Export control screening MCP that checks transaction parties, classifies dual-use technologies, and detects diversion routes — all from a single MCP tool call. Built for export compliance officers, defense contractors, semiconductor companies, and customs brokers who need fast, evidence-backed screening decisions.
MIT -
Autonomous-Security-Orchestration-Layergithub.com/ben854719/Autonomous-Security-Orchestration-Layerupdated this year
ACIS is a self-evolving cyber-immune system that uses telemetry and diagnostics to provide real-time, context-aware defense. Within seconds, it deploys digital antibodies, verifies each action with RS256, continuously simulates risk, and autonomously adapts to emerging threats.
Apache-2.0 ★ 1 -
as-redis-mcp-servergithub.com/zicheng-ai/redis-mcp-serverupdated this year
Read-only Redis AI Assistant for Qoder IDE - MCP Server with 8 semantic tools for key inspection, search, pattern analysis, health check, memory analysis, slowlog analysis, cache advisor, and readonly queries. Features deep-defense security: command whitelist, key prefix filter, data masking, rate limiting, and audit logging.
pypi MIT -
Self-hosted LLM gateway that turns flat-rate AI subscriptions (Claude Code Max, ChatGPT Plus, Codex, Copilot, M365, Gemini) into one OpenAI/Anthropic-compatible API. Unified subscription wallet, OAuth passthrough on /v1/responses, prompt-injection + PII defense, MCP server, semantic cache, time-travel replay.
Apache-2.0 ★ 15 -
Free security & privacy scanner for AI-coded apps. 766 rules, 84 MCP tools, 13-layer defense, zero-trust sandbox, AI firewall. Runs locally, never sends data anywhere. Scan your AI-generated app for leaked keys, open databases, and injection holes in 5 seconds.
npm MIT ★ 7 -
Prompt-injection defenses for Claude Code. A PreToolUse Bash hook blocks compositional credential-exfiltration shapes (secret read plus network, env dump to network, remote script to shell, reverse shells). A sanitizing MCP server wraps untrusted URLs and files in sentinels, strips invisible unicode, flags jailbreaks.
MIT ★ 4 -
nwc-mcpgithub.com/llmops-pro/nwc-mcpno update data
Gives any MCP client (Claude Desktop, Claude Code, Cursor, ...) a real Lightning wallet over Nostr Wallet Connect (NIP-47). 13 tools: balance, invoices, transaction history, and spend tools — bolt11, Lightning addresses, LNURL, batch pay, keysend. Every spend passes a defense-in-depth safety pipeline: budget caps (per-invoice / daily / total), destination allowlist, optional two-step confirmation, and an audit log. Works with Alby Hub or any NWC-capable wallet.
smithery -
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.
-
Declaw -- Secure AI Sandboxesno update data
Secure runtime for AI agents. Run AI agents and their tools in Firecracker microVMs with network policies, PII scanning, prompt injection defense, and audit logging. 7 tools: create_sandbox, run_command, read_file, write_file, list_files, kill_sandbox, list_sandboxes. Security presets (none / standard / strict) let you control guardrails per sandbox: restrict outbound traffic to specific domains, redact PII from command output, block prompt injections, and get full audit trails.
smithery -
Dockerfile linter with image-size and CVE advisories
NOASSERTION -
milstdlintgithub.com/cognis-digital/milstdlintupdated this year
Lint documents against MIL-STD / DoD formatting and classification-marking rules.
NOASSERTION ★ 1 -
ewcorrgithub.com/cognis-digital/ewcorrupdated this year
Correlate electronic-warfare event logs by time/frequency/bearing to cluster emitters.
NOASSERTION -
natosymbolgithub.com/cognis-digital/natosymbolupdated this year
Generate and validate APP-6/MIL-STD-2525 symbol identification codes (SIDC).
NOASSERTION -
classguardgithub.com/cognis-digital/classguardupdated this year
Validate classification banner markings (CUI/CONFIDENTIAL/SECRET) in documents per portion-marking rules.
NOASSERTION -
sigmetagithub.com/cognis-digital/sigmetaupdated this year
Parse and classify signal metadata (freq, modulation, bandwidth) into a normalized catalog.
NOASSERTION -
itarcheckgithub.com/cognis-digital/itarcheckupdated this year
Flags potential ITAR/EAR export-controlled terms and USML categories in code, datasheets, and docs.
NOASSERTION -
uasloggithub.com/cognis-digital/uaslogupdated this year
Counter-UAS telemetry/log analyzer that flags drone-detection events, RF bands, and track anomalies.
NOASSERTION