- Conduid
- Marketplace
- #ai-security
MCP servers tagged ai-security
796 live MCP servers tagged "ai-security", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with ai-security.
LLM Agent MCP Security Lab
Deliberately vulnerable local lab for hands-on LLM agent & MCP security testing; SSRF, path traversal, SQLi, indirect prompt injection, RAG poisoning, stored XSS and each with a S…
Lagrange
Byzantine Fault Tolerant consensus middleware that protects AI agent memory from poisoning attacks (MINJA, indirect prompt injection). Every write is validated by three independen…
Divergence
Precision-first security analyzer for MCP servers and agent skills. 0% false positives on traps, 96% recall.
Codelytra
Open-source, local-first AI security scanner for JavaScript and TypeScript LLM, agent, RAG, tool-calling, and MCP applications.
Eunox
A capability firewall for MCP servers: a deny-by-default proxy that enforces which tool calls an AI agent may make (and with which arguments), backed by a signed audit log. One st…
Agent Trust Plane
Authorization and security regression testing for AI agents and MCP tools.
Sentricore Agent Security
Security gateway for AI agents on REST and MCP: prompt-injection defense, tool governance, human-in-the-loop escalation, tamper-evident audit logs.
ThreatModel
Open-source, MCP-first threat modeling that proposes and sandbox-validates the fix — not just the report. Apache-2.0."
Svr Verify
Signed Verification Receipts for deterministic AI verification: CPU-only, Ed25519-signed, reproducible, independently verifiable.
Reachable Agent Plugin Installer
Claude Code marketplace for the REACHABLE plugin (generated from the signed adapter). Not the scanner.
Flowki Claude Code Hardening
Deny-list config, documented attack patterns, and pentester checklist from a hands-on security review of Claude Code's permission architecture.
Provekit MCP
Hardened MCP server that gives an AI agent a code security scanner, built so the tools can't be turned against the host, with a red-team suite that spawns the real server and prov…
State Of MCP Security
Reproducible security audit of MCP servers — 75% of scanned servers exposed a medium+ hardening issue to AI agents. Round 1: official reference + popular hosted servers.
Hexstrike Docker MCP
Dockerized HexStrike AI on a linuxserver.io Kali base image, with a remote streamable-HTTP MCP server exposing 150+ offensive-security tools to MCP clients like Claude Code.
Aitdp
AI Threat Detection Protocol — open spec, community ruleset and reference SDK for detecting prompt injection, jailbreaks, data exfiltration and tool abuse in LLM apps and AI agent…
Aie
Agentic Institution Engineering — portable semantics for authority, delegation, revocation, budgets, lifecycle, topology governance and evidence.
Heldfast
You approve an MCP server. Heldfast records what you approved. Later it tells you what moved, and guard refuses the rest.
Verus
Security infrastructure that converts untrusted financial content into verified, signed context for trading agents.
Configuration Drift Research
Security research on configuration drift in Model Context Protocol (MCP) deployments
Company Connectors
Secure MCP servers + gateway that connect Claude, ChatGPT, Cursor and other AI assistants to company systems (CRM, helpdesk, read-only SQL, docs, calendar/email). OAuth 2.1, per-r…
Secure MCP Gateway Lab
Secure MCP gateway lab covering authentication, least privilege, rate limiting, auditability, resilience, and integration tests.
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…
Agent Cve Scanners
Free offline scanners for 53 CVEs in 9 AI-agent frameworks + MCP tool pinning. No telemetry.
Aip Openclaw
AIP security plugin for OpenClaw: skill signing, capability manifests, runtime enforcement
Project Shield Docs
Project Shield v2.0.0 security scanner for AI/MCP projects — free local CLI; Pro is USD 29/month with automated Polar license fulfillment.
Claude Code Self Defense
Claude Code self-defense hooks — security hooks for AI coding agents
RogueAgent Testbed
Georgia Tech master's in cybersecurity research on cascading indirect prompt injection attacks. Author: Fahid Ahmed
Small Tools Lab
Local-first developer toolbox: browser utilities, explainable CLIs, and practical AI experiments.
Sleeper
Local-first agent tool-call assurance lab: injection → tool action → control gate → evidence.
Agentproof
Experimental assurance manifests and policy checks for AI agents and MCP integrations. Local CLI, synthetic fixtures and GitHub Action.
Claude MCP Allow
Generate least-privilege Claude Code permission rules for MCP tools from their live annotations: readOnlyHint tools go to allow, everything else to ask, one mcp__server__tool rule…
Agentic Semgrep Rules
Semgrep rules for AI agent code: static analysis for LLM applications in Python, TypeScript and JavaScript. Finds model output reaching exec, shells, SQL, URLs, files and HTML, us…
Skill Scan Gate
CI gate for Claude Code skills and plugins: scans a skills or plugin repository for instruction-override text, exfiltration patterns, dangerous hook commands, unpinned MCP servers…
Governance Proxy
MCP server that sits between AI agents and real systems. Evaluates every tool call before execution. Holds risky ones for human review.
Glyph
🔮 MCP security scanner — find tool poisoning, credential leaks, and insecure transports in AI agent configurations
Mitre Attack MCP
🔌 Exposes MITRE ATT&CK matrix lookup + tactic/technique mapper over MCP — MIT
Guard
Security scanner for MCP (Model Context Protocol) servers: detects tool poisoning, prompt injection, command injection, path traversal and leaked secrets. SARIF, GitHub Action, si…
AI Surface
Find and govern AI attack surfaces in application code, at PR time and inside your AI coding tool (MCP server, Claude Code hook). Free, OSS, runs offline.
Www Project Agent Memory Guard
OWASP Foundation web repository
Geiger
A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine
Vibesafe MCP
MCP server (not a Claude Code Skill) for the VibeSafe security scanner — scan code, live URLs and run a Launch Check from Claude Desktop, Claude Code, Cursor, Windsurf or any MCP…
AI Surface
Find and govern AI attack surfaces in application code, at PR time and inside your AI coding tool (MCP server, Claude Code hook). Free, OSS, runs offline.
Template
Secure MCP server template in TypeScript and Python: stdio by default, optional streamable HTTP behind bearer auth, rate limit and body cap, bound to 127.0.0.1; bounded file and n…
Docker
Govern consequential AI agent actions in Docker with deterministic policy, human approval, and signed Decision Dossiers.
Geiger
A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine
Www Project Agent Memory Guard
OWASP Foundation web repository
Scanner
Security auditing tool for MCP (Model Context Protocol) servers — 27 checks, web dashboard, SARIF output, compliance mapping
Firewall
Scan and gate Model Context Protocol servers for tool poisoning, rug-pulls, and indirect prompt injection.
Mcpguard
Local firewall, scanner, and audit logger for MCP servers. Auto-discovers Claude Desktop / Cursor / Windsurf / VS Code configs and flags risky tool servers — leaked secrets, curl|…
Decoy
Deterministic mcp decoy service with forensic dashboard