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.
-
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 -
Read-only local security gate & scanner for AI coding workflows, MCP, and package hallucination risks.
MIT -
LineBreak security gate at the git/CI boundary: dependency CVE scan + AI SAST, human-approved overrides, git-native audit records
pypi Apache-2.0 -
security-mcpgithub.com/abrahamoo/security-mcpupdated this year
AI security MCP server and enforcement gate for Claude Code, Cursor, GitHub Copilot, Codex, Replit, and any MCP-compatible editor. Applies OWASP, MITRE ATT&CK, NIST, Zero Trust, PCI DSS, SOC 2, and ISO 27001.
npm MIT -
zelsisactive
Check your code with Zelsis before you push: security and logic findings, release gate, MCP server for AI coding agents.
npm MIT -
Local-first AI agent orchestrator with MCP server, secure file operations, shell execution, code indexing, and quality gates
npm ISC -
wardloom-mcpactive
MCP server for Wardloom — trigger pre-deploy security scans, poll the ship-gate verdict, fetch remediation roadmaps and Dev/AI handoff prompts, and run zero-network local prechecks, all from your IDE's AI agent.
npm MIT -
vibecheckgithub.com/ArisRhiannon/vibecheckupdated this year
Offline, no-AI "safe to ship?" gate for vibe-coded apps — finds the security mistakes AI coding agents make (secrets, unprotected routes, eval-RCE, SQLi, CORS, JWT, leaked keys). CLI + MCP, agent-runnable.
MIT ★ 2 -
Binance Spot (security-first) + crypto analystgithub.com/Alejandrehl/kainext-binance-mcpno update data
Security-first Binance Spot MCP + honest crypto analyst. 25 tools, 5 prompts, human-gated orders.
pypi -
Human approval requests for agent actions: expiring, single-use decisions. Trusted executors must enforce the gate; not a same-user security boundary.
npm MIT -
Securely: a Touch ID-gated, encrypted Finder alternative for macOS with a local AI assistant (Ollama), semantic search, and MCP agent access. Experimental.
MIT -
Advisory NixOS change-review + CVE/KEV attestation gate for AI agents (MCP server). Grades security-relevant config diffs, attests closures against the CISA KEV catalog, gates on a human, keeps an append-only audit ledger.
MIT -
MCP server that exposes security tools to agents behind policy gates, sandboxing and an audit trail.
MIT -
xorb-mcpgithub.com/bidurkhatri/x.orbupdated this year
MCP server for X.orb — Security gating for MCP-connected AI agents
npm -
l5m-mcpgithub.com/jbrorepo/l5mupdated this year
MCP (Model Context Protocol) server exposing L5M security-gated memory to AI agents.
cargo MIT OR Apache-2.0 -
Self-hosted security scanner, autonomous pentest & QA agent, and production-readiness gate
AGPL-3.0 -
hotskillsgithub.com/epiphytic/hotskillsupdated this year
MCP server for hotskills — pre-configured skill management for Claude Code with security gating
npm MIT -
@blindkey/openclaw-skillgithub.com/michaelkenealy/blindkeyupdated this year
MCP server for BlindKey - secure credential injection and filesystem gating for AI agents
npm MIT -
pluto-aguardgithub.com/arshan846/pluto-aguardupdated this year
Security scanner and launch gate for AI agents & MCP apps — config scanning, policy coverage, risk modeling, drift detection, CI/SARIF, and launch-readiness evidence
Apache-2.0 ★ 4 -
Open-source quality gates for vibe coding: format, lint, security, impact, coverage, and AI review inside the agent loop (MCP + oracle). MIT.
MIT -
Capability-gated security reverse proxy and policy enforcer for the Model Context Protocol
MIT -
Policy-first AI security assessment planner with scope enforcement, approval gates, and typed MCP foundations.
NOASSERTION -
@shieldnet360/secure-vibegithub.com/shieldnet-360/secure-vibeupdated this year
SecureVibe — one binary for AI-assisted secure coding: secret / dependency / Dockerfile / GitHub Actions scanning, an offline OSV cache, a CI gate, 30 security skills, and an MCP server (secure-vibe mcp).
npm MIT -
claude-local-bridgegithub.com/suhteevah/claude-local-bridgeupdated this year
Access your local repos from Claude on your phone. Secure MCP bridge with approval gating, real-time dashboard, and tunnel support.
MIT -
Autonomous DevSecOps & Security Gate Agent with Model Context Protocol (MCP) for GitLab Duo (,000 Hackathon)
-
SkillSync MCP — security-gated skill management for Claude Code, OpenClaw, Cursor & Windsurf. 60+ threat pattern scanner.
npm MIT ★ 4 -
coldstar-mcpgithub.com/expertvagabond/coldstarupdated this year
Multichain MCP server for AI-agent secure transactions on Solana and Base -- reputation gating, DEX quotes, price feeds, balance checks, institutional custody vault tools
npm MIT -
Security engine for WordPress AI Abilities — fail-closed risk classification, permission gating, audit logging, and MCP/REST execution controls.
NOASSERTION ★ 2 -
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 -
Claude Code plugin for protect-mcp — MCP security gateway with per-tool policies, Ed25519-signed receipts, and human approval gates
MIT -
Security-first, self-hosted MCP and ChatGPT app for multi-mailbox IMAP intelligence with optional policy-gated Safe Send.
Apache-2.0 -
Enterprise multi-language security MCP — advanced taint, tree-sitter, plugins, SARIF/SBOM, policy gates, dashboard
MIT -
exa-gapped-mcpgithub.com/mikekelly/exa-gapped-mcpupdated this year
A fork of exa-mcp-server that routes requests through GAP (Gated Agent Proxy) for secure credential management. Provides Exa AI web search and code context tools via MCP.
npm MIT -
Safe-by-default MCP server for Toss Securities Open API with read-only market/account tools and gated order operations.
MIT ★ 2 -
@codesentrix/mcpactive
Code Sentrix MCP Server - AI Security, AgentShield Anti-Prompt Injection, and Quality Gates for Cursor, Claude, Antigravity, and Windsurf
npm Apache-2.0 -
Production-grade diagnostics, performance optimization, security auditing, and dead-code detection for Vue.js and Nuxt applications. Features automated codemods, CI quality gates, and AI agent integration (MCP).
npm MIT -
🦭 Secure-by-design AI-agent backend. Isolated by Postgres RLS, gated by human approval, pinned to its data residency. FastAPI · PydanticAI · MCP.
MIT ★ 1 -
MCP security trust layer. Scan packages, inspect repo MCP dependencies, generate Policy Gate setup, install the workflow directly, check exposure, and query abuse data.
npm MIT -
An MCP server, a policy-gated client, and the security layer between them — two processes, two mcp majors, 222 tests
MIT -
MCP server wrapping scope-gated recon/web-security CLI tools (nmap, sqlmap, commix, httpx, nuclei-class) as safe, audited MCP tools — HTTP service + Docker, integrates with RedPentAI.
NOASSERTION ★ 1 -
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 -
salamailerupdated this year
Zero-knowledge secure email CLI + MCP server — encrypt messages and attachments on your own machine, gate delivery with an SMS code or passphrase
npm MIT -
Scope-gated, modular security MCP server — 205 tools across 26 skill packs (red/blue/OSINT/cloud/AD/post-ex/IoT/Wi-Fi/AI-LLM/mobile/forensics/CTF) with an attack-path engine, credential vault & ATT&CK reporting. For authorized engagements.
MIT -
Secure MCP server exposing headless, out-of-process Ghidra (12.1.2) to LLM clients: read + consent-gated write reverse-engineering tools, with hardened disposable worker isolation.
Apache-2.0 -
@shieldnet360/securevibegithub.com/shieldnet-360/securevibeupdated this year
SecureVibe — one binary for AI-assisted secure coding: secret / dependency / Dockerfile / GitHub Actions scanning, an offline OSV cache, a CI gate, 30 security skills, and an MCP server (securevibe mcp).
npm MIT -
Secure file exchange for AI agents — scanned, provenance-stamped files behind expiring capability URLs, with human approval gates and Ed25519-signed receipts. MCP server + JS/Python SDKs.
npm MIT -
chain-signergithub.com/Kevthetech143/chain-signerupdated this year
Security suite for AI agents — catch the dangerous thing before signing: preflight EVM transactions for drains, inspect EIP-712 signatures for permit-phishing, and gate agent actions by policy. Pairs with any wallet/MCP stack; non-custodial wallet included.
pypi MIT ★ 1 -
Python dead code, security and secrets scanner with a pull-request gate; narrower checks for TypeScript, Java and more.
pypi Apache-2.0 -
Agentic API testing and security validation: AI agents that act only through a permission-gated, SSRF-guarded, audited MCP tool layer.
NOASSERTION -
Agentic API testing and security validation: AI agents that act only through a permission-gated, SSRF-guarded, audited MCP tool layer.
NOASSERTION -
argus-cigithub.com/venkatswaramoyya/argus-ciupdated this year
6-pass security & quality agent — Opengrep + Bearer + quality linter + ESLint/tsc + dep audit + Sonar — MCP server for Cursor/Claude + pre-commit gate
npm MIT -
Local-first activity monitor, deterministic policy gate, and universal security boundary for autonomous AI agents and Model Context Protocol (MCP) clients.
MIT ★ 1 -
Kotlin MCP server that maps app tech stacks to secure, fully provisioned AWS infrastructure via Terraform (+ Helm for EKS): generate → validate → plan → apply with checkov/kube-score security gating, infracost cost estimation, and drift detection.
MIT ★ 1 -
Secure Model Context Protocol (MCP) server for WordPress — bearer-token + OAuth 2.1 with PKCE, scope + capability dual-gate, audit log, brute-force lockout, 25 built-in tools.
GPL-2.0 -
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 -
Automate Cisco Secure Firewall (FMC-managed FTD) with Python, Ansible, and Terraform, plus three MCP servers that let an AI agent search policy, trace object usage, and propose changes behind a preview-and-confirm gate. Read-only by default, TLS on by default, CSV-driven, lab-tested.
MIT -
MCP server and agent skill that ships npm packages from GitHub securely: Snyk and npm audit scans, gated releases, trusted or staged npm publishing, SBOMs and verification reports, and public docs sync with private-data scanning.
npm Apache-2.0 -
Local-first MCP server for secure, content-minimized source inspection and capability-gated retrieval over stdio. Fail-closed and workspace-bound. | خادم MCP محلي لفحص مصادر مقلَّص المحتوى واسترجاع مشروط برموز قدرة عبر stdio. فشل مغلق وملتزم بجذور مصرّح بها.
Apache-2.0 -
clawpayergithub.com/valdo99/clawpayerupdated this year
Secure card vault with policy-gated payments for AI agents. MCP server + OpenClaw plugin.
MIT -
Security-hardened MCP server giving AI coding agents safe, deterministic, policy-gated access to local repositories
npm ISC