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.
-
cloud-audit-mcpgithub.com/badchars/cloud-audit-mcpupdated this year
Cloud security audit tools for AI agents — AWS, Azure, GCP misconfiguration detection via MCP. 38 tools, 60+ checks. The agent finds vulns, not you.
MIT ★ 23 -
Self-contained MCP security server that scores AI agent tool-calls with a rule-based library + behavioral detector, giving explainable, MITRE-mapped verdicts for known attacks
MIT -
Security auditor for AI agents and MCP servers — config analysis, prompt injection testing, tool probing, data flow tracing
npm MIT -
sentricore-agent-securitygithub.com/Pothan0/sentricore-agent-securityupdated this year
Security gateway for AI agents on REST and MCP: prompt-injection defense, tool governance, human-in-the-loop escalation, tamper-evident audit logs.
-
agent-security-lensgithub.com/professor2k8/agent-security-lensupdated this year
MCP security trust-check server for autonomous agents: safe install decisions, risk signals, controls and alternatives before installing MCPs, Skills or tools.
npm Apache-2.0 -
okalstergithub.com/0PeterAdel/okalsterupdated this year
Okalster — an open platform for autonomous security hunting agents powered by MCP, skills, and intelligent tool orchestration.
Apache-2.0 ★ 1 -
mcp-shieldgithub.com/rob925/mcp-shieldupdated this year
Static security scanner and MCP server for MCP servers and AI agent tools
MIT ★ 1 -
Governance layer for AI coding agents — model routing, security scanning, tamper-evident audit trail, JIT permissions. MCP server, 142 tools, 83 skill packs, 14 agent hosts, MIT licensed.
MIT -
MCP server that exposes security tools to agents behind policy gates, sandboxing and an audit trail.
MIT -
GitHub security posture audit tools for AI agents — organization, repository, Actions, secrets, supply chain analysis via MCP
npm MIT -
github-security-mcpgithub.com/badchars/github-security-mcpupdated this year
GitHub security posture analysis for AI agents — 39 MCP tools, 45 checks across org, repos, Actions, secrets, supply chain, and access control
npm MIT ★ 15 -
Blitz Strike — a universal MCP security-audit toolbelt. BLITZ sweeps the attack surface, EAGLE-EYE traces source-to-sink, STRIKE verifies live. 57 attack chains, 130-tool catalog, intelligence data layer. One server, every agent.
npm MIT -
High-performance zero-dependency static analysis tool enforcing NASA Power of Ten rules across 20 programming languages, plus AI agent skill, MCP server config, prompt template, and LLM model security auditing.
npm MIT -
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 -
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 -
Security check-up for APIs and AI agent tools: OWASP API Top 10 review of OpenAPI specs, headers, JWTs, release diffs and MCP tools, with fix code in 5 frameworks. Runs in the browser, the CLI and GitHub Actions.
MIT -
Connect AI agents to AuditHub’s blockchain security tools. Launch scans, review findings, monitor tasks. Open source, Apache 2.0.
Apache-2.0 ★ 22 -
A secure, highly capable MCP server written in Rust. It exposes a comprehensive suite of filesystem operations as tools for AI agents.
MIT ★ 6 -
Offensive-security tools, skills, and MCP servers for local AI agents — privacy-first, small-model-driven. Authorized pentest/red-team companion: 6 MCP servers (27 tools), all irreversible classes human-gated.
Apache-2.0 -
burp-mcpgithub.com/Den-Sec/burp-mcpupdated this year
Burp Suite Professional MCP server - 61 tools to drive Burp from an AI agent (Claude Code) for authorized security testing.
MIT ★ 3 -
owasp-agentic-mcpgithub.com/csoai-org/owasp-agentic-mcpupdated this year
OWASP Top 10 for AI Agents security assessment tools. Capabilities: full agent security scan, prompt injection detection, tool poisoning check, excessive agency, data leakage. Built by MEOK AI Labs.
pypi MIT License -
Provenance and priced risk for the MCP tools a Compound-facing agent calls: real MCP session, Ed25519 verification, risk weighted for Compound position exposure, and a priced report. A Compound Grants Program entry (Security Tooling). Testnet and seeded only.
MIT -
suprawall-mcp-plugingithub.com/wiserautomation/suprawall-mcp-pluginupdated this year
Official SupraWall MCP (Model Context Protocol) Security Plugin. Enforces deterministic guardrails, least-privilege tool access, and PII interception for AI agents.
★ 4 -
the-box-mcpgithub.com/horizonfps/the-box-mcpupdated this year
MCP daemon that gives an agentic coding client a native offensive-security toolchain: MITM proxy, app graph, OOB server, CVE/report RAG and 103 tools.
MIT ★ 2 -
MCP server security auditor — tool poisoning, ASCII smuggling detection, prompt injection, OWASP Agentic Top 10. First OSS tool for MCP security.
AGPL-3.0 ★ 2 -
MCP server giving AI coding agents (Claude Code, Codex, Cline) safe, structured network & security recon tools — DNS, WHOIS, TLS, and HTTP security headers, each with a graded verdict. Authorized testing & education only.
pypi MIT ★ 1 -
RedHands is an MCP (Model Context Protocol) server that exposes offensive security tools to AI agents.
MIT ★ 4 -
A local security checkpoint for AI agents. MCP firewall, Linux sandbox, secret inspection and auditable tool execution — built in Rust.
MIT ★ 1 -
qualys-mcpgithub.com/rijul170/qualys-mcpupdated this year
MCP server for full Qualys portal management — VMDR, Policy Compliance, WAS, Cloud Agent, Container Security, TotalCloud, Patch Mgmt, CSAM/GAV, EASM & admin. 59 modules, ~400 tools, read/write/destructive safety tiers.
pypi MIT -
MCP server for a catalogue of 167 paid agent tools on x402 (USDC/Base), including AgentGuard: signed, independently verifiable security verdicts for MCP tool surfaces.
npm MIT -
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 -
MCP server that gives AI agents authorized-only offensive-security tools: recon, CVE intel, JS analysis, port scanning
pypi 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 -
MCP server interface for AI agent and MCP security auditing — config analysis, trust audits, prompt injection testing, tool probing, and data flow tracing
npm MIT -
Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.
npm NOASSERTION ★ 15 -
The in-guest execution agent. Runs security tooling and the MCP bridge inside a Setec microVM. Elastic License 2.0.
NOASSERTION -
Check a website's security in plain English from the terminal, or give your AI agent the tool. Free, no key.
npm MIT -
MCP server that gives AI agents a local security scanner before they install or trust third-party tools.
oci MIT ★ 4 -
Security-first agentic AI on AWS — Strands agent + Claude Opus 4.6 on Bedrock AgentCore | MCP tools secured via SigV4/IAM, OAuth2 M2M (Cognito + AgentCore Identity vault, zero embedded secrets), and Amazon Verified Permissions per-tool authorization | re:Invent SEC307
★ 1 -
MCP server: free web tools for AI agents — HTML→Markdown, EU compliance scan, page profile, security headers. Zero auth, zero dependencies.
npm MIT -
agent-smithsgithub.com/daletoniris/agent-smithsupdated this year
MCP-based autonomous security agent with LLM-powered analysis, multi-tool orchestration, and automated reporting
MIT ★ 1 -
Agent-native web security: a human and an AI agent inspect and fix an authorized site together, via six WebMCP tools on document.modelContext. Passive-only, human-approved. Built for the OpenAI WebMCP Challenge.
MIT -
AgentGuard is an open-source, local-first MCP security gateway that protects AI agents with policy-based tool permissions, human approvals, audit logs, and policy simulation. Developed by Belfeki.tn.
Apache-2.0 -
Provenance-aware security gateway for MCP: stops untrusted tool output from turning into agent actions
MIT -
Two-component system bridging Kali Linux penetration testing tools with AI agents via MCP. Flask API server executes 10+ security tools (Nmap, SQLMap, Metasploit, etc.) while MCP client provides seamless AI integration for automated security workflows.
MIT ★ 9 -
Kubernetes security audit agent - declarative kagent agent with MCP tools and privacy-preserving pseudonymization via LLM proxy
Apache-2.0 ★ 1 -
AgenticStore: The secure toolkit for AI agents. Instantly equip Claude Desktop, Cursor, and Windsurf with 75+ MCP tools, persistent memory, and SearXNG search, all protected by a built-in PII prompt firewall to protect your data from being exposed to AI agents.
pypi MIT ★ 5 -
lazysshgithub.com/MauricioPerera/lazysshupdated this year
Secure dual-interface SSH: a human TUI plus agent-safe CLI and MCP tools.
-
🔌 Exposes OWASP Top 10 for Agentic AI security over MCP — prompt injection detection, tool poisoning, excessive agency, data leakage assessment
pypi MIT -
Security for AI agents: 8 MCP tools - config audits, secret redaction, skill vetting, network scans, agent-native checkout
Apache-2.0 -
Read-only MCP tools that help AI agents explain security and system health on Windows devices and Linux home servers.
nuget MIT -
Offline cyber security agent for your apps and AI coding tools. Open R&D: measured in public, improved every release.
npm MIT -
Secure MCP server exposing Convertigo tools, resources, prompts, recipes, and token administration to AI coding agents.
-
Read-only MCP server over Atrio: three tools for an AI agent, scoped by PostgreSQL Row Level Security, tested over the protocol.
MIT -
Open-source AI agent security gate: deterministic ALLOW/BLOCK/ESCALATE authorization before every tool call, plain-English policy compilation, tamper-evident audit ledger. MCP security gateway + Claude Code/Cursor guardrails. Rust, Apache-2.0.
Apache-2.0 -
Read-only AWS security audit tools for AI agents, served over the Model Context Protocol. Contract-tested, eval-gated, least-privilege by design.
pypi MIT -
Cybersecurity-MCPgithub.com/LiamTCollins/Cybersecurity-MCPupdated this year
A tool to add to an agent's repertoire to improve security of AI created apps and sites.
Apache-2.0 -
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 -
Hercules MCP is a Model Context Protocol server that gives AI Agents, the ability to perform professional penetration testing. It orchestrates a fully containerized Kali Linux environment, exposing industry-standard offensive security tools as structured MCP tools that agents can reason about and drive autonomously.
MIT ★ 6 -
Agentic API testing and security validation: AI agents that act only through a permission-gated, SSRF-guarded, audited MCP tool layer.
NOASSERTION