- 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.
Auditrail
Tamper-evident audit-log aggregator with hash-chained attestation
Ghaudit
Audit a GitHub org's security posture (branch rules, 2FA, secrets) from an export
Cspbuilder
Generate and audit a Content-Security-Policy from a page's resources
Dnsaudit
DNS posture & misconfiguration scanner — SPF/DKIM/DMARC/DNSSEC/CAA
Nightprism
MCP-native security scanner that asks "should I ship tonight?" for AI-generated code.
Tool Calling
A runnable demo using an MCP server demonstrating secure MCP best practices with a refund_order tool that moves money.
Seosiri API Guard MCP Server
A sovereign, universal API validation and multi-industry compliance security MCP server supporting OWASP, HIPAA, PCI-DSS, GDPR, and SEO/AEO metadata guardrails.
Sentinel Trace
🛡️ Catch unsafe AI agent actions before they execute — explainable risk scoring, injection detection, and real-time containment powered by SigNoz & OpenTelemetry.
LLM Secret Manager
The secret manager for LLM agents: create, rotate, and use secrets they can never read. OS-native keyvault (macOS Keychain) + zero-dependency MCP server + Claude Code guard hook.…
Kinopipe MCP
Remote MCP server for KinoPipe: typed video editing (FFmpeg as a service) for AI agents. 39 tools, OAuth 2.1, async jobs, signed outputs.
TalonHound
Self-hosted threat intelligence and IOC management platform
Security Readiness Guide
Security checklist, threat model, and production readiness standard for Model Context Protocol (MCP) servers.
Jasswiki
JassWiki - Die digitale Jass-Enzyklopädie
Jak Shield
Secure AI agent tool calls by blocking destructive actions, redacting sensitive data, and enforcing human oversight with this universal security gateway.
Maskprompt MCP
MCP server: redact PII (emails, phones, credit cards, SSNs, IPs, secrets) from text before it leaves your control.
Sec Hydra MCP
MCP server for THC-Hydra - Password brute-forcer for authorized penetration testing
Italian Workplace Safety
MCP Server for Italian Workplace Safety (D.Lgs 81/08) — query ATECO codes, training schedules, glossary, sanctions, regulations from Claude Desktop, Cursor, Cline, Windsurf. Power…
Facturepro MCP
Electronic invoice processing & compliance (Peppol, Chorus Pro)
Qso Graph Auth
Persona and credential management for qso-graph MCP servers
Vcp
VCP — Verifiable Capability Protocol: zero-trust capability execution for AI agents. A stricter sibling of MCP where models plan and a signed gateway enforces. Signed content-addr…
Pre Tool Gate
MCP server for Claude Code: Pre-execution policy gate for tool calls.
Incident Intel
MCP server wiring PagerDuty, Dynatrace, and runbook context for AI-driven incident response
Nameguard
Check an MCP server's tool names against the names agent frameworks reserve for their own tools (tool shadowing)
Kali Ssh MCP
MCP server bridging Claude/any LLM client to a persistent Kali Linux VM over SSH — scope-gated nmap, gobuster, nuclei & nikto with structured JSON output and full audit logging.
Safe Runbook MCP
Policy-gated MCP server for version-controlled operational runbooks with dry-run planning and out-of-band approvals.
For Your App
Why you need an MCP server for your app — an honest lead-magnet pack: the argument + a skill to build the reachable path safely + a skill to audit your app's MCP/analytics/securit…
Agent Plugins Doctor
Validate, diagnose, and safely fix Agent Plugins, Agent Skills, MCP configs, compatibility, and portability issues.
Claude Obsidian Memory
Give Claude Code a memory that survives between sessions, stored as plain Markdown in your Obsidian vault.
Mcpg Plugin Audit Http
HTTP collector audit sink: batches audit events into bearer-authenticated JSON POSTs
Mcpg Plugin Credential Jwt Mint
JWT-minting credential_issuer plugin for MCPG (dev.mcpg.credential.jwt-mint)
Boundary Audit
Detects MCP tools hidden from tools/list yet reachable via tools/call; the bundled mock reproduces FAIL and PASS. Actively calls operator-named tools; 11 tests, CI. Does not disco…
Adjent
Evidence for what autonomous software does. Conformance checking and signed, verifiable records of agent actions.
Obsidian Collaboration MCP
A small, safe MCP server that lets ChatGPT and other agents read and write an Obsidian vault.
Gumi MCP
Servidor MCP local, somente leitura, que expoe um repositorio a agentes de IA sem expor os dados que vivem dentro dele
Dgb Digiid MCP
Give an AI agent a verifiable identity via Digi-ID: prove who it is by signing a challenge, no passwords. Pairs with DigiByte agent payments.
Service Demo
Evidence-first MCP incident response demo integrating Splunk, a service catalog, and a service desk.
Netauto
Read-only multi-vendor network automation, exposed to agents over MCP and to people over a web GUI. Reads device state, audits configuration against rules that reference the vendo…
AI Development
Enterprise AI-guardrails template. Shared CLAUDE.md/.cursorrules policy, secret-hygiene scaffolding, and MCP deployment checklists for human and AI coding agents.
Coffee Desk MCP
Demo mcp server for coffeedesk.app (mcp.coffeedesk.app)
Deepseek Oracle MCP
MCP server that provides expert-level DeepSeek V3.2 queries via OpenRouter API for Claude Code agents
Edgedelta AI Agents Enhancement
17 new MCP tools for EdgeDelta AI agents — enhanced monitoring, observability, and security automation
SkillWatch
Independent, local-only watcher for the AI-skill supply chain: flags bait-and-switch changes in the pages skills and MCP tools reference. Sends nothing anywhere. Python CLI.
Sec Nikto MCP
MCP server for Nikto - Web server vulnerability scanner
Antidote
Security scanner for MCP tool servers that detects poisoning, injection surfaces, and propagation paths
Tessera Anchor Log
Public-facing append-only anchor log for Tessera certificates. Each commit adds an anchor record (Merkle root + leaves + OpenTimestamps proof reference).
Firebase Security MCP
MCP server for Firebase Firestore Rules security audits inside Claude Code, Cursor, Cline.
Shopify Hermes Oauth
Hermes-first Shopify OAuth connector for agent-safe multi-store access, read-only reporting, guardrails, audit logging, and MCP integration.
Aincore
AinCore — 本地 AI 算力平台。基于 Electron + llama.cpp 在你的设备上安全运行 GGUF 大语言模型，提供 UDS JSON-RPC 服务、OAuth 2.0 授权、隐私哨兵、应用市场等核心能力。
Stillvault MCP
MCP server for Stillvault — human-approved secret release for AI agents, without the secret entering the model's context.
Security Docker Gateway
Vulnerable MCP server + layered defenses (static scan, runtime interceptor, Docker MCP Gateway).