1. Conduid
  2. Marketplace
  3. #agent-security
Tag

MCP servers tagged agent-security

47 live MCP servers tagged "agent-security", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with agent-security.

47
live servers
49
avg trust
662
most stars
1

Nono

always-further

Sandbox any AI agent in seconds - zero setup, zero latency.

★ 662updated 6 months agoApache-2.0
87
2

Template Repo

AndrewAltimit

Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers

★ 110updated 6 months agoUnlicense
83
3

Medusa

Pantheon-Security

AI-first security scanner with 76 analyzers, 4,000+ detection rules, 508 FP filters (96.8% reduction), and 133 CVE detections for AI/ML, LLM agents, and MCP servers

★ 172updated 6 months agoAGPL-3.0
80
4

Gateway

lasso-security

A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.

★ 349updated 7 months agoMIT
79
5

Cupcake

eqtylab

A native policy enforcement layer for AI coding agents. Built on OPA/Rego.

★ 188updated 6 months agoApache-2.0
77
6

Agent Security Scanner MCP

sinewaveai

Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis,…

★ 68updated 6 months agoMIT
77
7

Compliant LLM

fiddlecube

Build Secure and Compliant AI agents and MCP Servers. YC W23

★ 158updated a year agoMIT
75
8

agentos-server

git+imran-siddique

[DEPRECATED] Moved to microsoft/agent-governance-toolkit

★ 67updated 6 months ago
67
9

Honeymcp

barvhaim

Open-source honeypot for MCP (Model Context Protocol) servers. Collects threat intel on attacks against the AI agent ecosystem.

★ 18updated 6 months agoNOASSERTION
66
10

Agentic Security

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

64
11

Mcptrust

mcptrust

Runtime security proxy for MCP: lockfile enforcement, drift detection, artifact pinning, Sigstore/Ed25519 signing, CEL policy, OpenTelemetry tracing. Works with Claude Desktop, La…

★ 6updated 8 months agoApache-2.0
59
12

Arcjet Js

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS…

59
13

Agentseal

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP serv…

52
14

Secure Claude Code

Security guardrails for Claude Code, MCP tools, and Claude cowork workflows. Local-first modular YARA-style guard packs for secrets, exfiltration, prompt injection, MCP abuse, and…

52
15

Reins

Runtime security for OpenClaw agents. Scan, fix, monitor.

52
16

Sponsio

Deterministic safety solutions for probabilistic AI agents

52
17

Adrian

Runtime security monitoring and control for AI agents. Catches malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

52
18

Prismor

Runtime security for Agents. Blocks dangerous commands, prevent secret leaks, stop prompt injection, gate risky package installs and visibility and control over tool calls.

52
19

Penetration Testing

Mr-Infect

The ultimate OWASP MCP Top 10 security checklist and pentesting framework for Model Context Protocol (MCP), AI agents, and LLM-powered systems.

★ 9updated 8 months ago
48
20

nickpending/mcp-recon

nickpending

Reverse-engineer MCP server tool surfaces. Enumerate, fuzz, classify, report. CLI + library.

★ 25updated a year ago
46
21

Helm AI Kernel

Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.

44
22

Clawseccheck

🦞 Local, read-only security scanner for OpenClaw. Finds config, prompt-injection and supply-chain risks — A–F grade.

44
23

Multi Agent Workflow Lab

Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.

44
24

Opena2a CLI

Unified CLI for the OpenA2A security platform

42
25

Aegis Memory

Secure context engineering for AI agents. Content security · integrity verification · trust hierarchy · ACE patterns. Self-hosted, Apache 2.0.

39
26

Agent Mesh

[DEPRECATED] Moved to microsoft/agent-governance-toolkit

39
27

Signet

Cryptographic action receipts for AI agents — sign, audit, verify.

39
28

Bluerock

Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as structured NDJSON. No code changes. Apache…

39
29

Dcp

Permission layer for AI agents — wallet signing, vault access, budgets, and human approvals.

39
30

Authsome

Local credential vault for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.

39
31

Trustabl

Static analyzer for agent reliability.

39
32

Cyvisguard

Security control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP. Guards a real Claude Code end to end.

39
33

ADR

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

39
34

Ryk

Guardrails for coding agents. Run Pi, Hermes, OpenCode, Codex, or Claude through ryk with policy, approvals, 86 safety packs, and a local audit trail.

39
35

Agentaudit

Security scanner for AI agent packages — CLI + MCP server

37
36

Install Guard

Scan MCP servers before installing them

37
37

Risk

Audit MCP configs and servers for risky tools, secret exposure, and prompt-injection patterns.

37
38

Nominee

Decision-bound Model Context Protocol tool handlers for governed AI agents

37
39

Tool Gateway

Local-first governed tool execution gateway for AI agents. Read/write classification, policy evaluation, signed execution receipts, multi-key rotation with cross-signed chain snap…

37
40

Golf Scanner

Discover and audit MCP servers for security vulnerabilities across Claude Code, Cursor, VS Code, and more

34
41

Mcps Ha

High Availability extension for MCPS – signed state sync, nonce replication, rogue server detection. Install on top of mcp-secure.

34
42

Sint Protocol

Open protocol and reference stack for governing AI agent actions in physical and safety-critical systems

34
43

sint-ai/sint-protocol

risk audits.

34
44

Mythos Sentinel

Agent permission firewall for MCP tools, shell, files, and x402/Base payments.

34
45

Patient Zero

Supply-chain attack scanner for the agent era. Triage in 30s with `npx patient-zero`, block malicious installs before postinstall runs, or drop into CI as a GitHub Action. Covers…

34
46

Firmis Scanner

AI agent runtime security scanner - detect malicious behavior in Claude Skills, MCP Servers, Codex Plugins, and more

34
47

askalf/truecopy

mcp proxy exposes only pinned, unmodified tools from a live server.

34
← Previous Page 1 of 1 Next →