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.
-
Open-source browser toolkit for HSM key management, payment security, PKI, cryptography, and MCP tools.
npm MIT ★ 4 -
🛡️ Open-source MCP server for AI-powered DevSecOps — cloud audits, CVE scanning, secrets detection, K8s security & more.
npm MIT ★ 1 -
Open-source security audits for Supabase: a read-only MCP server, a CLI agent and a Claude Skill. Finds RLS misconfigurations, exposed keys and risky functions, and returns a scored report with fix SQL. Hosted version: Locksoup.
MIT ★ 50 -
Tetherplane is an open-source MCP server for authorized AI computer use: secure files, terminal processes, browsers, desktop automation and remote devices.
NOASSERTION ★ 1 -
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 -
Open-source, read-only security checks for apps built with AI: leaked keys, exposed files, open panels, vulnerable Next.js. CLI, GitHub Action and MCP server.
AGPL-3.0 -
Open-source web security verification workspace: OWASP-aligned dynamic scanning, local static analysis, evidence-based OpenVEX drafts and an MCP server.
Apache-2.0 ★ 2 -
Live security incidents with fix status, fixed versions and sources. MCP server, JSON/RSS feeds, lockfile check. Docs and issues only; the site's code is not open source.
CC-BY-4.0 -
Open-source MCP server for native macOS apps. 71 tools, 13 services, 100% local. Security audited.
MIT ★ 4 -
Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.
Apache-2.0 ★ 92 -
Open-source MCP server for querying ZeroPath security issues, patches, and scans using Claude, Cursor, Windsurf, or any AI assistant.
MIT ★ 11 -
Open-source security inspection for MCP configurations and tool metadata. Run locally from the CLI or inside your coding assistant.
npm MIT ★ 3 -
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 -
IslamicCorpusMCPgithub.com/ayzekhdawy/IslamicCorpusMCPupdated this year
Secure open-source MCP server for the Islamic Text Corpus (Quran, Hadith, Tafsir) — stdio/SSE/streamable-http, Bearer auth, anti-hallucination
MIT -
agentshieldgithub.com/sohailshaikh20/agentshieldupdated this year
Identity & access security for non-human identities. Open-source, starting with AI agents and MCP.
npm 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 -
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 -
Open-source RAG platform built with Python and FastAPI for secure document search, grounded AI answers, source citations, and optional MCP integration.
MIT -
shocgithub.com/pwnera/shocactive
Open-source, headless, AI-first SOC for companies with no security team: one container and Postgres, driven over MCP, REST, CLI and Slack.
Apache-2.0 -
calsetagithub.com/calseta/calsetaupdated this year
The open-source data layer for security agents. Ingest, normalize, enrich, and expose security alerts via REST API and MCP server.
Apache-2.0 ★ 7 -
Python-Runtime-Interpreter-MCP-Servergithub.com/hileamlakB/Python-Runtime-Interpreter-MCP-Serverstale
PRIMS is a lightweight, open-source Model Context Protocol (MCP) server that lets LLM agents safely execute arbitrary Python code in a secure, throw-away sandbox.
MIT ★ 30 -
noxgithub.com/Nox-HQ/noxactive
Open-source security scanner with first-class AI app security (prompt injection, embedding leakage, agent over-privilege, MCP hardening). Polyglot AIBOM, SARIF, SBOM. Cosign-signed plugin marketplace. Offline-first, agent-native via MCP.
Apache-2.0 ★ 11 -
Argus — open-source security scanner (SAST, secrets, malware heuristics, SARIF, MCP). YAML rules welcome — good first issues.
go MIT ★ 10 -
Offline security scanning for AI-generated code: seven open-source scanners and AI-specific checks in one command.
pypi Apache-2.0 -
Open source security for AI agents: an OS-enforced egress wall on macOS, and on Ubuntu 24.04 x86-64 via a separate package; keys only the operator holds; a hash-chained audit record. One command wraps Claude Code, Cursor, Hermes, OpenClaw or Cline on tested config paths. No vendor in the path. Claims trace to the Assurance Matrix.
npm Apache-2.0 ★ 10 -
Open-source Application Security Posture Management: scanning, findings lifecycle, SBOM, AI-assisted review (cloud or local models) and MCP - Docker-first
Apache-2.0 -
Open-source AI cybersecurity harness to build & deploy continuous security agents that find, prove, fix and monitor vulnerabilities across code, binaries, dependencies, infrastructure. Web UI, CLI, CI and MCP.
Apache-2.0 ★ 1,371 -
zngithub.com/usezn/znactive
The local security layer for coding agents. Use Claude Code, Codex CLI, Cursor, OpenCode, Antigravity or the ZCode desktop app without exposing your secrets, your data or your systems. Open source (MIT), no account, nothing sent by default.
npm MIT ★ 5 -
Offline security scanning for AI-generated code: seven open-source scanners and AI-specific checks in one command. It finds secrets, vulnerable, hallucinated and malicious dependencies, poisoned agent configuration, and infrastructure and code flaws. An MCP server for Claude Code and Kiro, and a CLI. Your source never leaves your machine.
pypi Apache-2.0 -
fortimail-mcp-servergithub.com/Lynsoft/fortimail-mcp-serverupdated this year
Open-source MCP server for FortiMail Engine: 40+ tools, Bearer auth, caching, stdio or HTTP — secure AI gateway without appliance passwords.
MIT ★ 1 -
Daily dashboards for open-source organizations, built from public data on a published method. Open edX: health grades for ~170 repositories across 9 metrics. Pressingly/Moneta: how far each fork has drifted from its upstream, with releases and security advisories. Read-only MCP endpoint for AI agents.
AGPL-3.0 ★ 1 -
altais-mcpgithub.com/gl-tches/altais-mcpupdated this year
Modular, open-source MCP server providing comprehensive security analysis for AI coding agents.
npm MIT -
Fast, AI-first web security testing toolkit in Rust: an open-source alternative to ZAP, Burp Suite and the like. Intercepting proxy, scanner, fuzzer and reports, as a JSON CLI with an MCP server and a desktop app.
Apache-2.0 ★ 13 -
A secure, open-source Model Context Protocol server for the Openlane GRC platform.
oci Apache-2.0 ★ 3 -
NSAuditor AI Community — open-source network security scanner. 27 discovery plugins, structured findings, SARIF/CSV output, MCP integration, optional local or cloud AI analysis. No telemetry; scan data never leaves your machine for Nsasoft. MIT licensed.
MIT ★ 24 -
free, open-source plugins for Claude Code & Cowork — Google Drive, WhatsApp, YouTube, WordPress, Apollo & more. Built on the SOSA™ security framework.
MIT ★ 11 -
quandashi-trademark-mcpgithub.com/qds2026/quandashi-trademark-mcpupdated this year
Open-source MCP adapter for securely connecting AI clients to Quandashi trademark data services.
MIT -
An open-source, local-first Model Context Protocol (MCP) server for **Secure Live Database Querying, Schema Inspection, AWS S3 Security Audits, and Cloudflare Infrastructure Control**.
pypi MIT -
MCP server for AgentSkillsHub — search, audit, and install open-source AI agent skills & MCP servers from inside your agent. Security-graded, quality-scored. Zero backend load.
npm MIT -
Security tripwires for AI agents. MCP tools that detect prompt injection, credential theft, and unauthorized tool calls in real time. Open source, zero dependencies, works with Claude Desktop, Cursor, Windsurf, VS Code, and Claude Code.
npm MIT ★ 1 -
Local-first MCP security scanner for AI-generated apps: four open-source engines plus the Synvoya engine. Scan → fix → rescan from Claude Code, Cursor, Codex, and other agents.
npm Apache-2.0 ★ 51 -
Open-source OSINT reconnaissance toolkit — domain intel, subdomain enum, DNS/SSL/WAF analysis, email harvest, and 16 MCP tools for Claude Desktop integration. Python 3, security-hardened.
GPL-2.0 -
An open-source, AI-native Model Context Protocol (MCP) server bridging Large Language Models with core network diagnostic tools for automated observability, threat detection, and agentic security orchestration
★ 1 -
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 -
Open-source AI reverse-engineering workspace with a desktop app, red / blue / both analysis, parallel Goals, a security knowledge base, and MCP tools for Ghidra, Frida, x64dbg and Rizin.
Apache-2.0 ★ 1,371 -
Analyze NextDNS logs and query statistics, review security and privacy settings, and manage allowlists and denylists from ChatGPT. Independent, open-source MCP integration with previewed, user-approved changes.
MIT -
mcp-osvgithub.com/gleicon/mcp-osvupdated this year
A MCP (Model Context Protocol) server to allow code security reviews using https://osv.dev (Open Source Vulnerabilities Database)
★ 15 -
🚀 AI-powered CI/CD pipeline analyzer for Azure DevOps & GitHub. Automatically enforces security policies, detects vulnerabilities, and posts compliance reports on PRs. Open source DevSecOps automation.
Apache-2.0 ★ 2 -
The Model Context Protocol (MCP) is an open-source implementation that bridges Jenkins with AI language models following Anthropic's MCP specification. This project enables secure, contextual AI interactions with Jenkins tools while maintaining data privacy and security.
pypi mit -
FHIR-MCP is an open-source MCP (Model Context Protocol) server that enables LLMs to securely interact with FHIR servers and HL7 terminology services. It provides a comprehensive toolset for healthcare interoperability with built-in PHI protection, audit logging, and token-efficient operations.
MIT -
Open-source secure device access for users and AI agents via MCP, CLI and API
MIT -
The Model Context Protocol (MCP) is an open-source implementation that bridges Jenkins with AI language models following Anthropic's MCP specification. This project enables secure, contextual AI interactions with Jenkins tools while maintaining data privacy and security.
pypi MIT ★ 160 -
Your own cybersecurity engineer, watching over you 24/7. Free, open-source Mac security agent that uses your own AI, or one running fully on your Mac, to explain what it finds in plain words. Nothing changes without your Touch ID.
MIT ★ 2 -
Roteador MCP self-hosted e open source (MIT): delega tarefas de texto/código a vários modelos de IA com failover automático, memória de missão compartilhada entre harnesses (Claude, Codex, Hermes) e subagentes paralelos por papel (architect, backend, frontend, security, QA, devops, reviewer). Node.js 22+, sem dependências de runtime.
MIT -
zexio-zmsgithub.com/zexio-io/zexio-zmsupdated this year
ZMS (Zexio Secret Management System) is a high-performance, open-source secret management ecosystem. Featuring Blind Indexing, Shamir's Recovery Shards, and native Model Context Protocol (MCP) support. Built for developers who demand security without the complexity.
NOASSERTION -
Open-source, read-only AWS security scanner. 110 checks across 25 services, 31 attack-chain rules, 64 IAM escalation methods (incl. lateral AssumeRole graph), Proof Mode exploitability verification, data perimeter and Bedrock AgentCore checks, Blast Radius CLI, Threat Feed, What-If simulator, AI-SPM, 6 compliance frameworks, breach-cost estimation, MCP server. CLI + Terraform remediation on every finding.
pypi MIT -
Electric Blue MCP provides a Dockerized MCP server exposing a curated set of open‑source recon and application security tools (nmap, nikto, sqlmap, dirb, dnsrecon, wpscan, searchsploit, grype, syft). All tool calls are sanitized, time‑capped, output‑truncated.SBOM and vulnerability scanning to support supply chain visibility.
★ 1 -
Open-source MCP server connecting AI agents to enterprise data — with hard guardrails, predictable costs, and security first.
MIT -
Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.
pypi MIT ★ 7,889 -
altais-mcpgithub.com/gl-tches/altais-mcpupdated this year
A modular, open-source Model Context Protocol server that provides comprehensive security analysis for AI coding agents
npm MIT ★ 1