- Conduid
- Categories
- Security
Security MCP servers
Security MCP servers indexed by Conduid, ranked by trust score. 4.9K live listings from GitHub, npm, PyPI and the official registry, each with a 0–100 score, security checks, and install commands.
Dpo2u MCP AI
DPO2U MCP AI — Model Context Protocol server for LGPD compliance AI agents
SDK Private Org
Enterprise MCP server scaffold — auth middleware, RBAC, audit logging, and deployment patterns for private org AI tooling infrastructure
Security Evidence Redactor
Dependency-free JSON findings summary that emits severity counts without copying finding details.
Bathy
Agent-native network discovery. Typed MCP tools, evidence-backed findings, deny-by-default scope enforcement.
Nimbus SDK
Nimbus Agent — SDK (@nimbus-dev/sdk). MIT, dependency-free TypeScript contract for authoring Nimbus MCP connectors & extensions.
Subject Broker
An experimental MCP context broker: one process per subject, default-deny policy, fail-closed audit — with field-tested evidence on agent delegation.
Velum MCP
VELUM by Abogado Virtual. MCP de privacidad para abogados. Anonimización local de documentos jurídicos y controles para usar IA sin exponer información confidencial.
Celestial Autofarm
Local-only Potassium MCP bridge with bounded tools, Protocol 2 mutual authentication, and Apache-2.0 licensing.
Brasilapi MCP
An authored Model Context Protocol (MCP) server exposing the public BrasilAPI (CEP, CNPJ, banks, FIPE, holidays, DDD) as tools. No API key required; tests run fully offline.
Shipmcp
Turn an OpenAPI spec or local script into a production-ready MCP server in minutes.
Worksmobile MCP
Unofficial NAVER WORKS (LINE WORKS) Drive admin CLI + MCP server — service-account delegation, shared-drive permission management
Toolprint Watch
Daily observation of public MCP servers. The git history of baseline.json is the dataset.
Medsguard Agent
An LLM-driven medication-logging agent with a deterministic safety spine.
Mojaq
Read-only MCP server for MOJAQ — ask Claude, Claude Code or Cursor about your EU-hosted app deploys, errors, logs, uptime and incidents.
Hw Verify MCP
MCP server giving AI agents a hardware constant-time, masking, and patch-completeness checker they cannot argue with
Warder
A policy gate for MCP tool calls. Blocks destructive AI agent actions before they run — as the subprocess your AI client launches, where network gateways can't see.
Audit Scanner
Read-only AST security scanner for Python Model Context Protocol servers before connecting them to AI clients.
Kipimo
Swahili agent-task evaluation suite — model-agnostic seed benchmark for the East Africa coordination stack (46 tasks; golds machine-derived from authoritative sources).
Smcp
Semantic ontology bindings for Model Context Protocol (MCP)
Mcpg Plugin Credential Oauth Client Credentials
OAuth 2.0 client_credentials credential_issuer plugin for MCPG (RFC 6749 §4.4)
Celestial Potassium MCP Legacy
Standalone read-only Potassium MCP bridge with bounded inspection tools, Protocol 2 mutual authentication, and Apache-2.0 licensing.
Safemcp Gateway
MCP security gateway with zero dependencies - blocks prompt injection, path traversal and SSRF attacks on AI agents.
Zastava
MCP gateway in Rust: argument-level policies ("github, but only repo X"), audit log, and rules learned from observed behaviour.
Agent Mail MCP
Send physical mail from an AI agent. An open MCP server for agent-payable mail - print and post real letters and postcards via x402, with tool schemas for Claude, LangChain, and O…
Pcap MCP
Secure MCP server for AI-assisted PCAP analysis with tshark, redaction and prompt-injection defense.
Cancerbero
Local, offline-first GGUF and llama.cpp pre-load inspector
Verified Giving Protocol
Verified Giving Protocol (VGP) - an open standard letting nonprofits declare their authorized giving pathways, with WebMCP tools and the VGPify skill.
Sideshift MCP Server
Official Cursor plugin for SideShift's hosted MCP server.
Ainumbers
Deterministic fintech compliance tools + the OpenChainGraph verifiable-artifact standard
Xche AI App Security Pack
Free security guardrails for apps built with AI coding tools (Claude Code, Cursor, Lovable, Bolt). Drop-in rules + OWASP/LLM/MCP policy + secret-scanning hooks & CI gate.
Prompt Injection Defense
The language-level attack defense skill every agent should keep. Covers 12 attack categories. Works with Claude, GPT, Gemini, Copilot, and any LLM.
Devparana Incident Agent Mcps
Projeto criado para Talk no DevPR 2025
Oura Ring MCP Server
Oura Ring API model context protocol implementation
Openssh Poc Expl
zero day exploit to get remote access to any server running openssh (unpatched)
Moonbunny
execute lua scripts on remote devices using mcp and grpc
Pythonide Link
Universal Links, share previews, remote imports, and MCP OAuth callbacks for PythonIDE.
Verification Security
Public verification, security review, and skill quality process for Agent Skill Exchange
Salva
Salva Runtime — self-hosted discovery intelligence runtime (API / MCP / CLI / SDK)
Vibegroup Protocol
📦 Wire protocol and Zod-validated envelope schema for vibegroup: sealed question/answer messages between Claude Code agents.
Statedrift
git log for your infrastructure — tamper-evident host snapshots, diffable history, and drift rules for Linux (and your AI agent's config)
Voice Command
Local voice input/output layer for authorized MCP clients; adds speech without adding new tool privileges
Soc Stack
One-command self-hosted SOC lab for Proxmox: Wazuh, TheHive, Cortex, MISP, Zeek, Suricata, and MCP servers for homelab blue-team training.
Forsety
Evidence layer for licensed AI data access — Built on Shelby Protocol
Mindio Magic MCP
Secure MCP server for WordPress with OAuth 2.1, content automation, and native Flatsome UX Builder support.
Rutile
Least-privilege secrets broker for AI agents
Amos Agent
Open-source native operator for the governed AMOS company brain — model-independent, locally capable, and human-governed.
Capability Ledger
Infer least-privilege MCP tool policies from agent traces
Roelint
Turn Rules of Engagement into a policy firewall for red-team commands and AI agents
Dsh Wind Aifin
Credential-safe Wind AIFin MCP and Alice integration for DeepSeek Harness.
Sec Scanner
Comprehensive security scanner for Model Context Protocol (MCP) servers