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.
-
—
Apache-2.0 ★ 1 -
atomic-red-team-mcpgithub.com/cyberbuff/atomic-red-team-mcpupdated this year
MCP server providing access to Atomic Red Team security tests with search, validation, and creation capabilities
pypi MIT -
MCP server for Structured robustness/security testing
npm ISC -
🔌 Exposes red-team-ops tools over MCP (MEOK AI Labs).
MIT -
Zero-dependency LLM red-team scanner: 24 attack probes across 9 classes (44/20 in PRO), honest refusal-aware verdicts, Markdown report, x402 USDC + Nano paid tiers
MIT -
Autonomous cyber red team intelligence for AI agents — this MCP server gives Claude, GPT-4o, and any MCP-compatible agent the ability to run quantitative attack simulations, synthesize exploit chains, forecast vulnerability emergence, and model adversary behavior using eight rigorously implemented mathematical frameworks.
MIT ★ 1 -
garbleworksgithub.com/SamsonCyber/garbleworksupdated this year
Authorized LLM red-team harness: recipes, scoped fire, evolutionary search, Wilson ASR. MCP + API + TUI.
Apache-2.0 -
pyrit-mcp-servergithub.com/Nislive/pyrit-mcp-serverupdated this year
Arm any MCP-capable agent to autonomously red-team a target LLM. Microsoft PyRIT exposed as 31 composable MCP tools: attacks, scoring, converters & scenarios
MIT ★ 1 -
Grounded red-blue adversarial plan refinement via MCP — tree-sitter fact extraction + LLM red/blue team analysis
Apache-2.0 -
Autonomous Offensive Security Agent for Red Team Operations
Apache-2.0 ★ 4 -
@rotalabs/redqueengithub.com/rotalabs/rotalabs-redqueen-jsupdated this year
Quality-diversity evolutionary red-teaming for LLMs and agents (single-turn, multi-turn, agentic/MCP)
npm AGPL-3.0-or-later -
sentinelpipegithub.com/S0TORU/sentinelpipeupdated this year
Evidence-first LLM and agent red teaming with a local workbench, CLI, and MCP server.
Apache-2.0 -
Agent-powered red team testing workbench with asset mapping, threat modeling, multi-agent workflows, cloud assessment, reports and MCP.
MIT ★ 47 -
⚔️ Autonomous red-team swarm for AI apps, agents & MCP servers — pentest your agent before someone else does.
Apache-2.0 ★ 2 -
k11techlab-llm-assurance-toolkitgithub.com/K11-Software-Solutions/k11techlab-llm-assurance-toolkitactive
LLM red-teaming & assurance toolkit: 41 OWASP LLM Top 10 probes, CI quality gate, audit-ready HTML reports, Claude LLM-judge and an MCP server for agent-driven red-teaming.
pypi MIT ★ 2 -
TrustModel MCP Server — trust evaluation, red-team, and governance for AI agents via the Model Context Protocol. npm: @trustmodel/mcp-server
-
LLM agent that investigates suspicious files over MCP and returns a cited verdict, with a prompt-injection red-team harness.
MIT ★ 1 -
binevalgithub.com/darksolitaire9-hub/binevalupdated this year
A deterministic, Rust-native binary evaluation kernel for AI safety, designed to help autonomous agents self-correct and red-team LLM infrastructure without fuzzy scores.
MIT -
TrustModel MCP Server — trust evaluation, red-team & governance for AI agents via the Model Context Protocol. Public canonical home of @trustmodel/mcp-server.
npm ★ 1 -
Sliver C2 MCP Server — 104 tools for AI-driven red team ops (Claude Code, Codex). Full session/beacon parity, loot, websites, rportfwd, taskmany.
MIT ★ 1 -
promptarmor-plugingithub.com/allsmog/promptarmor-pluginupdated this year
LLM security red teaming — Claude Code plugin + MCP server with 80+ attack plugins and 25+ mutation strategies
MIT ★ 1 -
MCP server for Canary Court: a NEAR testnet market where AI agents red-team AI agents. No tokens or API keys needed.
npm MIT -
Attack your AI agent before your users do: reliability and red-team testing for any AI agent, as a CLI, Claude Code plugin and MCP server.
Apache-2.0 -
MCP server that lets an LLM read chats, voice notes and images and draft replies, behind a tested send gate and a 15-case red-team eval.
MIT ★ 1 -
SleepyWalkergithub.com/bidhata/SleepyWalkerupdated this year
🛡️ Autonomous SQL injection pipeline — crawls, probes, confirms with AI, exploits with sqlmap, reports in HTML/JSON/SARIF. Built for authorized red teams. One command, full database. Go · OpenRouter AI · chromedp · MCP
★ 1 -
rogue-live-redteamgithub.com/nguiasoren/rogueupdated this year
Continuous open-web LLM red-team: harvests live jailbreaks from 15+ open-web sources, reproduces them against your model x system-prompt x tools, and serves results over its own MCP server.
pypi MIT -
sentinelmcpgithub.com/MusaIslamFahad/sentinelmcpupdated this year
An automated red-teaming and reliability-auditing platform for AI agents - tests for prompt injection, tool hijacking and data exfiltration. Ships as an MCP server.
MIT ★ 2 -
ShadowEdge — single-binary red-team collaboration: asset center, 11-phase board, DAG attack paths, finding lifecycle, MCP, master/edge sync. 单文件红队协同平台:资产中心、11 阶段作战板、DAG 攻击路径、漏洞生命周期、MCP 与主从同步。
MIT ★ 1 -
meok-mcp-hardening-mcpgithub.com/csoai-org/meok-mcp-hardening-mcpupdated this year
MEOK MCP Hardening MCP — automated security red-team for any MCP server. Maps OWASP LLM Top 10 (2025) + 5 MCP-specific risks to a 0-100 hardening score with HMAC-signed reports. By MEOK AI Labs.
pypi MIT -
atlasgithub.com/2005-Aneeshdutt/atlasupdated this year
Automated LLM red-teaming pipeline: a LangGraph agent runs jailbreak, prompt-injection, hallucination and bias attacks against a model, scores responses with an LLM judge, mutates failed attacks, and reports results in a Streamlit dashboard and MCP agent.
MIT ★ 1 -
Glass Box Framework — runtime constitutional verification for AI answers. Trust Cards with claim-level reasoning chains, formal ECS scoring, the 7-angle Glassbox Court red team, and deterministic audit logs. MCP-native.
pypi Apache-2.0 ★ 10 -
provekit-mcpgithub.com/Th3Circle-app/provekit-mcpupdated this year
Hardened MCP server that gives an AI agent a code security scanner, built so the tools can't be turned against the host, with a red-team suite that spawns the real server and proves the trust boundaries hold.
MIT -
Conversational Arabic + English AI assistant on live market data: LangGraph pipeline, LLM provider failover, 14 typed tools, safe text-to-SQL on SQLite or PostgreSQL, saved chats, charts, MCP server, red-team tests, 1,296-case eval.
MIT -
Claude-native, governed offensive-OSINT & external attack-surface platform for authorized red-team and bug-bounty. Multi-agent recon across web, identity, cloud, secrets & breach intel under deterministic scope/evidence/approval controls, with human-reviewed findings for hand-off to pen-testing. Not an exploitation framework.
NOASSERTION ★ 15 -
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 -
adversagithub.com/cognis-digital/adversaupdated this year
LLM red-team harness — OWASP LLM Top 10 + MITRE ATLAS attack packs
NOASSERTION -
RedTeam-MCPgithub.com/RedTeamMCP/RedTeam-MCPupdated this year
Red Team MCP - provides configurable AI agents and multi-agent coordination
AGPL-3.0 ★ 4 -
hydra-mcp-servergithub.com/fnarel/hydra-mcp-serverupdated this year
Red Hat API MCP Server - Fork with enhancements for team use
★ 1 -
hermes_mythic_mcpgithub.com/null-event/hermes_mythic_mcpupdated this year
AI Copilot for macOS Red Teaming: MCP Server for Hermes Mythic C2 Agent
★ 1 -
juridica-mcp-servergithub.com/probonoapps/juridica-mcp-serverupdated this year
MCP server for Jurídica — search Panamanian law, calculate labor settlements, and red-team legal arguments. Powered by x402.
MIT -
spectyn-secopsgithub.com/markl-a/spectyn-secopsupdated this year
Multi-agent SecOps research playground — red/blue team simulation built on phantom-mesh. MCP server exposing recon/exploit/detect/respond tools to Claude Code, Cursor, or any MCP-compatible runtime.
NOASSERTION -
Agentic pentest & red-team harness via Burp Suite MCP toolkit
Apache-2.0 ★ 9 -
sentinel-flight-recordergithub.com/dmetagame/sentinel-flight-recorderupdated this year
MCP-native execution safety and red-team benchmark for autonomous Bitget trading agents
MIT -
llamator-mcp-servergithub.com/RomiconEZ/llamator-mcp-serverupdated this year
MCP server for llamator: automate LLM red teaming workflows
CC-BY-SA-4.0 ★ 4 -
thinking-toolsgithub.com/PranayMahendrakar/thinking-toolsupdated this year
Five rigorous reasoning protocols - debate, red team, argument audit, threat model, study sanity. Free MCP plugin for Claude and ChatGPT, zero extra credits.
MIT -
GlassTape Policy Builder is an AI-powered MCP server (integrating with Cursor, AWS Q, and Claude) that turns natural-language security requirements into production-ready Cerbos YAML policies, enabling security teams to govern AI agents and applications with policy enforcement through automated generation, validation, and red-teaming of guardrails.
Apache-2.0 ★ 3 -
ramibotgithub.com/RamiBotAI/ramibotupdated this year
RamiBot v3.8.0 is a local-first AI security operations platform integrating multi-LLM support, a dynamic red/blue team skill pipeline, MCP tool orchestration, Docker terminal access, Tor proxy management, and an auto-integrated Kali-based tool server (rami-kali) for controlled, extensible offensive and defensive workflows
MIT ★ 29 -
seculo-perdidogithub.com/pedropasinn/seculo-perdidoupdated this year
Wiki de evidências sobre o mistério central de One Piece: hipóteses ranqueadas, átomos verificáveis, red team adversarial e um validador que recusa afirmação sem fonte.
MIT -
juridica-mcp-servergithub.com/juridicapanama/juridica-mcp-serverupdated this year
MCP server for Jurídica — Panamanian legal AI platform. Search 10,500+ legal articles, red-team legal arguments, and calculate labor/notary fees.
npm MIT -
🚀 Automate LLM red teaming workflows with the MCP server for LLAMATOR, featuring asynchronous job handling and seamless integration.
CC-BY-SA-4.0 ★ 2 -
arenagithub.com/tim101010101/arenaupdated this year
Multi-agent AI arena for debates, code reviews, and red-team challenges via Model Context Protocol (MCP)
npm MIT ★ 1 -
backtest-auditoractive
Backtest Auditor: a red-team lint for trading strategies (static lookahead/bias lint, Deflated Sharpe, cost and stability audit), as a Python library and an MCP server.
pypi Apache-2.0 -
FourEyesgithub.com/LoganLuo46/FourEyesupdated this year
Human-gated support agent: dual MCP servers, LangGraph interrupts checkpointing before every irreversible write, three defense layers red-teamed against prompt injection.
MIT -
Fenceline — a red-team range and loss-bound report for AI agent wallets on NEAR. GuardVault contract, Rust policy engine, MCP server, Noir ZK circuit, Next.js MVP.
MIT -
LitterBoxgithub.com/BlackSnufkin/LitterBoxupdated this year
A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.
pypi GPL-3.0 ★ 1,571 -
A pricing war room for concentrated commodity markets, served over the Agent Client Protocol (Zed, JetBrains) and MCP. Game theory, demand estimation and an honest red team.
-
Hexstrike-redteamgithub.com/Yenn503/Hexstrike-redteamupdated this year
AI-powered MCP penetration testing framework combining HexStrike's 150+ security tools with BOAZ's advanced payload evasion (77+ loaders, 12 encoders). Features 12+ autonomous AI agents for bug bounty, CTF, CVE intelligence, exploit generation, and red team operations.
pypi ★ 174 -
One command installs 670+ security tools on Debian/Ubuntu/Kali, Fedora, Arch, openSUSE and Termux. Its authorization-gated MCP server runs them in a disposable Kata Containers VM sandbox for Claude Code, Codex, Gemini CLI, OpenCode and other MCP clients. 872 agent skills for CTF, pentesting, bug bounty, DFIR and red/blue teams.
oci MIT ★ 98 -
Open-source MCP control plane for AI coding agents: mechanical time-locks, evidence-gated proof receipts, red-team remediation, and persistent engineering memory.
pypi MIT ★ 26 -
MCP server over a COIN wargame engine: any host model plays Government or Red Team through tools; seeded replayable games; model benchmark harness. Protocol 2026-07-28.