- 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.
Hackerone MCP
Zero-dependency MCP server exposing HackerOne's public GraphQL API as AI-agent tools: discover bounty programs, scopes, and recently solved reports.
Pre Tool Gate
MCP server for Claude Code: Pre-execution policy gate for tool calls.
Parimit
Proposal-only payment-intent governance for AI agents: deterministic policy, demo human review, hash-linked audit evidence, REST, MCP, and mock outcomes—without a live payment rai…
Mcpinterlock
Policy firewall and audit layer for MCP tool calls. Fixed an SSRF bypass where hostnames resolving into RFC 6598 CGNAT shared address space (100.64.0.0/10) weren't blocked -- Pyth…
Gitops Safe MCP
Read and validation-only GitOps MCP server for OpenTofu and Ansible
Scopecheck
Static security auditing for Python MCP servers, trace reachable capabilities and incomplete analysis without executing target code.
Safe Runbook MCP
Policy-gated MCP server for version-controlled operational runbooks with dry-run planning and out-of-band approvals.
Audix MCP
Audix MCP server for AI-assisted smart contract security fuzzing.
Obstat
An auditable decision record for agent tool calls. The clearance is written down before the call runs.
Agent Plugins Doctor
Validate, diagnose, and safely fix Agent Plugins, Agent Skills, MCP configs, compatibility, and portability issues.
Security News MCP Researcher
Local-only security news researcher: RSS inbox triage, Claude-powered research chat with pluggable MCP tools, and weekly security-meeting notes generation.
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…
Flink MCP Enterprise Server
Production-grade governed MCP server for Apache Flink secure-by-default tools for REST & SQL Gateway with approval tokens, policy engine, DLP, audit, and Prometheus telemetry.
Adjent
Evidence for what autonomous software does. Conformance checking and signed, verifiable records of agent actions.
Gumi MCP
Servidor MCP local, somente leitura, que expoe um repositorio a agentes de IA sem expor os dados que vivem dentro dele
Starter Demo
Runnable TypeScript MCP server demo with tested tools, official SDK protocol proof, and CI.
Launchcheck
Safe, local-first preflight diagnostics and reproducible failure bundles for MCP servers.
Shadow MCP Scanner
Find the MCP servers on your network nobody registered, and classify what they hand an anonymous caller.
Sandboxaq
SandboxAQ — independent third-party profile of a public API surface, by API Evangelist. SandboxAQ (SB Technology, Inc.) builds Large Quantitative Models (LQMs) — AI systems that f…
Sec Nikto MCP
MCP server for Nikto - Web server vulnerability scanner
Sec Subfinder MCP
MCP server for subfinder - Subdomain discovery
Antidote
Security scanner for MCP tool servers that detects poisoning, injection surfaces, and propagation paths
Firebase Security MCP
MCP server for Firebase Firestore Rules security audits inside Claude Code, Cursor, Cline.
Edge Soc MCP
A Cloudflare Workers MCP server that puts a SOC analyst's enrichment, investigation, and detection-context workflow behind a single endpoint, and runs on a free Cloudflare account.
Claude Box
A capability-secured box for agent sessions — its authority is the door references it holds (keeper/scout/concierge/net), parent-agnostic.
Pnx MCP Audit
Security audit CLI for Model Context Protocol (MCP) servers. Zero deps, offline, cross-platform.
Bert Bouncer
On-device prompt-injection firewall for Claude Code. Hybrid DeBERTa + masked-LM detection with span localization, content sanitization, and a reproducible red-team evaluation. No…
Patch
Static security scanner for Python MCP server code. Detects shell injection, SSRF, path traversal in @tool functions.
Helix Sandbox
Secure sandbox MCP server for AI agents — Docker and Windows Sandbox backends
Vault Server
Zero-trust key management MCP server — AES-256-GCM, Circuit Breaker, IAM labels, Cloud Armor WAF
Check Please
Reliant AI's secure credential broker for AI coding agents + 16-provider API key audit pipeline. CLI, TUI, Web, Desktop, MCP, HTTP API.
1api
Scoped data gateway for AI agents — give Claude safe, audited, revocable access to your private database
Leak2lock Installer
Public installer metadata for Leak2Lock
Agenthusk
Local-first forensic scanner for secrets and risky residue left by AI coding agents.
Toolhutch
Local-first permission auditor for agent tool manifests.
Elder Council Harness
A local-first, multi-model council harness for high-stakes decisions — risk-gated escalation, fail-closed consensus, hash-chained audit. Eight councils (six cyber + a general busi…
Verum
Deterministic, whole-program, multi-language code analysis
Toolseal
A lockfile for MCP server capabilities
Hooklint
Offline linter for the agent config that actually executes: hooks, skills, MCP entries, permission rules. Catches the hook that can never fire and the hook that splices agent-cont…
Guarded Server
An MCP server with a real security model and the tests that prove it: three permission tiers with human approval for destructive tools, a path jail, tool results marked as untrust…
Kimi Code Security Hook
PreToolUse security gate for Kimi Code: blocks secret exposure & SSRF before WriteFile/Shell via correctover-scan (MCP config security)
Mailbridge MCP
Security-first, read-only email intelligence reference app for MCP and ChatGPT.
Native MCP Sandbox
Capability-bounded Linux evidence: C++20 MCP authority boundary, bounded Python orchestration, and adversarial assurance.
Skill Lock
package-lock.json for AI agent skills: hash-pin skills, agents, hooks, plugins & MCP config; detect tampering across sessions
Pc Filebridge
Create-only filesystem MCP server with bounded reads for ChatGPT, Codex, and compatible clients.
Sentnelops Python
Python SDK for SentnelOps — MCP firewall, agent identity, runtime policy, and audit evidence for AI agents
Security Index
MCP Security Index 2026: security posture of the 50 most widely used public MCP servers — per-call authorization, audit logging, caller auth, destructive capability, documented CV…
Webmcp Sentinel
Server-enforced authorization, human approval, and audit for AI-agent actions — a WebMCP security reference implementation
Vulconcern
The Nx s1ngularity attack used your own AI CLI to steal credentials via a postinstall script. Offline, read-only scanner for tampered configs, MCP endpoints, credential files, and…
Lazyssh
Secure dual-interface SSH: a human TUI plus agent-safe CLI and MCP tools.