- Conduid
- Marketplace
- #security
MCP servers tagged security
4.8K live MCP servers tagged "security", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with security.
Android MCP Bridge
Consent-first Android companion exposing selected device capabilities as an authenticated local MCP server
Otaviocc Obsidianmcpserver
A Model Context Protocol (MCP) server that enables AI assistants to interact with your Obsidian vault
Prop Firm Rules (FloorGuard)
Sourced prop-firm daily-loss and max-drawdown rules and a drawdown-room checker. Read-only, no auth.
Monologue
See what your AI agents did in one private feed. Read other agents' reports with permission.
com.shippdf/pdf
Author PDF templates and generate documents from them.
Sitelemetry
OAuth website audits: security, SEO, AI visibility, integrations, accessibility and performance.
MeshVault Connectors
Read-only tools: EMS protocols, courts and judges, NPI and FDA data, GPU fit for open models.
LovedOne Family MCP
Family inbox: read records; invite, reply, mint codes. API key or OAuth care_circle:write.
AIKI Knowledge Commons
Authenticated MCP access to the AIKI open knowledge commons.
Commonhold
Read-only MCP door to Commonhold, a public society for AI agents. No credential needed.
leaks.md and confession.md
Anonymous, encrypted disclosure of AI alignment and safety failures, with signed receipts.
Silk
Message other people's AI agents with consent: end-to-end encrypted, on a public ledger.
Ntsb Investigations
NTSB Investigations — aviation accident/incident investigations by
Cratis Chronicle
Inspect Cratis Chronicle event stores read-only by default; opt-in, authorized job control.
MoneyMatter
Personal finance tracker: accounts, transactions, budgets, investments and analytics over OAuth.
Claude Connector for Odoo
Permission-aware MCP server for Odoo 18/19. OAuth 2.1; each call runs as one named Odoo user.
TehProf Support
Helpdesk tickets from your AI: find, reply, take, hold, complete — within your own role. OAuth.
Certpatrol
TLS cert lifecycle & rogue-issuance watch via Certificate Transparency
Res Ex Machina
⚖️ Neutral and automated registry where AI agents leave a verifiable trail of their creations. EIP-712 signatures, L2 blockchain anchoring, production-grade security. SDK on npm.
Samar MCP
🛡️ Ephemeral privacy & security middleware for Model Context Protocol (MCP). Zero-persistence credential masking & fail-closed execution guard for AI agents.
Overspend Challenge
Pink Overspend Challenge: try to make an AI agent break Pink Agentic AI Payments' spending rules (test money). 3 of 3 bounties claimed; Hall of fame open.
Audit Go
Go reference implementation of MCP Admission Control Extension (#3004) — CICS PCT → ATSA audit checkpoint
Asitis Agent Tools
Read-only MCP server and Claude Code plugin that lints CLAUDE.md, AGENTS.md and SKILL.md, counts approximate tokens per file, flags hidden instructions and invisible characters, a…
Valvur
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 depende…
Vulngate
Agent-neutral security checks before you ship — SAST, secrets, and dependency audit as a merge gate. Find, understand, and fix vulnerabilities in AI- or human-written code. BYO-in…
Patchpilot MCP
MCP server for npm package security scanning using OSV API
Dssguard
Commit only the tool effects an MCP declaration permits: a drop-in proxy that checks readOnlyHint/destructiveHint at runtime and rolls back violations.
Deterministic Safety Sandboxes With MCP
Dependency-free Python MCP server that puts a deterministic policy boundary in front of subprocess execution for agents.
Omnicode
Self-hosted MCP hub: register an MCP server once from your phone and use it in Claude Code, Codex CLI and Gemini CLI. OAuth on the hub, secrets never reach agents. MCP 2025-11-25…
Agentsift
Security scanner for AI agent plugins, skills, and MCP packages. npm audit for the AI agent ecosystem.
Skillgrade
Trust layer for Agent Skills and MCP packages: lint, scan, doctor, and CI summaries.
Aip Openclaw
AIP security plugin for OpenClaw: skill signing, capability manifests, runtime enforcement
Pi Secrets Guard
Block secrets and PII before they land: regex + entropy scanning for files, diffs, and AI coding agents (CLI + MCP + skill + pi extension).
Beachead
Desktop app for managing AI agents in isolated Docker Sandbox microVMs
Agentic Compliance Checker
Self-verifying LLM agent for repo/IaC assessment against code-detectable NIST 800-53-inspired controls, with evidence-backed verdicts and evals.
AI Invictum Browser Bridge
Security-first MCP bridge that lets AI agents control your existing Chrome profile locally, visibly and safely.
Snapgauge
Contract tests for MCP servers: snapshot schema and behavior, then fail CI when the next version moves.
Skill Audit
Проверка чужого скилла, плагина или MCP-сервера Claude до установки: сеть, ключи, персистентность, обфускация, промпт-инъекции. Сканер только читает.
Still Untrusted
From-scratch TypeScript reimplementation of Microsoft Agent Framework's FIDES label algebra, checked against its spec.
SentinelFlow Console
SentinelFlow 离线安全检查控制台 + CTF 解题 Agent（本地知识库 / 自主学习 / 真实执行层）
Thoropass
Thoropass — independent third-party profile of a public API surface, by API Evangelist. Thoropass is an auditor-led, AI-powered compliance and audit automation platform that combi…
Nixreview
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…
Modelcontextprotocol Ext Auth
RDF parse data for modelcontextprotocol/ext-auth
Fencepost
Fencepost: a firewall and scanner for MCP servers used by AI agents.
PII MCP Server
MCP Server for PII
Application MCP Server
Reusable MCP server integration, authorization, audit and agent skills for PHP applications.
Musespark MCP
MuseSpark MCP Bridge exposes your WordPress business (posts, Yoast SEO, WooCommerce products & stock, newsletter, daily reports) as standardized MCP tools, with a built-in OAuth 2…
Autopia
Verified, reproduced behavior of public HTTP APIs: spec gaps, errors, pagination, auth.
Agent Financial Advisor
Compliance, risk, tax and audit checks for AI trading agents: pre-trade, sizing, wash sales, Reg BI.
JFSecure
Let AI agents use secrets without seeing them: masked output, every use approved in JFSecure.