Security

25,252 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

mcp

2593

frogeye-ai/mcp

MCP server Claude CodeCodexCursor +2

Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns. Remote server at mcp.frogeye.ai.

not rated 0 4mo ago A tokens not measured

onepassword-agent-mcp

2594

gambadio/onepassword-agent-mcp

MCP server Claude CodeCodexCursor +2

Local MCP access to approved 1Password fields without exposing plaintext secrets to AI agents. Runs locally from the onepassword-agent-mcp npm package.

not rated 0 2d ago A tokens not measured original MIT

gitlumen-mcp

2595

gitlumen-team/gitlumen-mcp

MCP server Claude CodeCodexCursor +2

Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals. Remote server at mcp-github-screen.gitlumen.com.

not rated 0 3mo ago A tokens not measured

gsep-mcp

2596

gsepcore/gsep-mcp

MCP server Claude CodeCodexCursor +2

AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts. Runs locally from the @gsep/mcp npm package. Needs 4 environment variables to run.

not rated 0 3mo ago A tokens not measured

defi-guard-mcp

2597

iinniitt/defi-guard-mcp

MCP server Claude CodeCodexCursor +2

DeFi safety checks on Base before you sign: honeypot, owner-power scan, approval risk, Aave health. Runs locally from the @iniit/defi-guard-mcp npm package. Needs 1 environment variable to run.

not rated 0 2mo ago A tokens not measured original MIT

mcp-server

2598

ingressward/ingressward-mcp-server

MCP server Claude CodeCodexCursor +2

Block prompt injection, evasive spacing, and obscene content before it reaches your LLM. Runs locally from the @ingressward/mcp-server npm package. Needs 1 environment variable to run.

not rated 0 3mo ago A tokens not measured

mcp-defectdojo

2599

inspicere/mcp-defectdojo

MCP server Claude CodeCodexCursor +2

MCP server for DefectDojo vulnerability management — 24 tools with RBAC, HMAC audit chain, and SIEM forwarding. Runs locally from the mcp-defectdojo Python package. Needs 6 environment variables to run.

not rated 0 3mo ago A tokens not measured original MIT

secret-safe-env

2600

irrenwill/secret-safe-env

MCP server Claude CodeCodexCursor +2

Write secrets into .env without the agent ever seeing the value - Windows masked dialog (繁中 UI). Runs locally from the secret-safe-env npm package.

not rated 0 3mo ago A tokens not measured original MIT

rag-mcp

2601

jaimenbell/rag-mcp

MCP server Claude CodeCodexCursor +2

Minimal, honest RAG-over-a-corpus MCP retrieval tool: searchknowledge(query, k) -> cited chunks. Local embeddings + embedded vector store. Auth-scoped, fail-soft, version-pinned. Runs locally from the jaimenbell-rag-mcp Python package.

not rated 0 10d ago A tokens not measured original MIT

rails-mcp

2602

jaimenbell/rails-mcp

MCP server Claude CodeCodexCursor +2

Self-hosted, caller-configured default-deny action registry + append-only spend ledger + human sign-off audit trail, exposed as MCP tools. classify() is unconditional GATED -- that invariant is never configurable. Governance/safety flagship: stop an agent from doing something irreversible without a human noticing.…

not rated 0 1mo ago A tokens not measured original MIT

lazaretto

2603

jamesdfinance-dev/lazaretto-mcp

MCP server Claude CodeCodexCursor +2

Free lockfile malware check plus paid pre-install scan of any skill, tool, or package. Runs locally from the lazaretto-mcp npm package.

not rated 0 13d ago A tokens not measured original MIT

consentgate-mcp

2604

jessepetersondev/consentgate-mcp

MCP server Claude CodeCodexCursor +2

Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed. Runs locally from the consentgate-mcp npm package. Needs 2 environment variables to run.

not rated 0 3mo ago A tokens not measured original MIT

mcp-audit-server

2605

joepangallo/mcp-audit-server

MCP server Claude CodeCodexCursor +2

Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend. Runs locally from the ledd-mcp-audit-server npm package. Needs 2 environment variables to run.

not rated 0 21d ago A tokens not measured original MIT

a2a-trustgate

2606

jyswee/a2a-trustgate

MCP server Claude CodeCodexCursor +2

A2A TrustGate: 4-gate firewall that screens every AI-agent action before it runs. 49 tools. Runs locally from the a2a-trustgate npm package. Needs 2 environment variables to run.

not rated 0 1mo ago A tokens not measured

secretcarousel

2607

jyswee/secretcarousel

MCP server Claude CodeCodexCursor +2

Agent-first secrets vault. Store, rotate, and share credentials from chat. 20 tools. Runs locally from the secretcarousel npm package. Needs 1 environment variable to run.

not rated 0 1mo ago A tokens not measured

netintel-mcp

2608

kjgueye/netintel-mcp

MCP server Claude CodeCodexCursor +2

MCP server for NetIntel — DNS, SSL, WHOIS, email security, OSINT via x402 micropayments. Runs locally from the netintel-mcp npm package. Needs 1 environment variable to run.

not rated 0 2d ago A tokens not measured

bridgeguard-mcp

2609

kota1026/quantum-shield

MCP server Claude CodeCodexCursor +2

One of 6 in

BridgeGuard MCP Server - Cross-chain bridge security audit tools for AI coding agents. Scan bri... Runs locally from the bridgeguard-mcp npm package.

not rated 0 16d ago A tokens not measured original MIT

bot-factory

2610

laser54/telegram-managed-bot-factory

MCP server Claude CodeCodexCursor +2

A secure MCP control plane for Telegram Managed Bots. Runs locally from the telegram-managed-bot-factory Python package.

not rated 0 8d ago A tokens not measured original MIT

mcpwatch

2613

lazymac2x/mcpwatch

MCP server Claude CodeCodexCursor +2

Audit MCP servers from inside Claude Code. 10 OWASP checks, A-F grade, live leaderboard. Runs locally from the mcpwatch-mcp npm package.

not rated 0 3mo ago A tokens not measured original MIT

agent-guard

2614

liminalpepe/agent-guard-mcp

MCP server Claude CodeCodexCursor +2

Verify-before-act safety MCP for AI coding agents: check packages, lockfiles, skill/plugin manifests, and CI workflows before installing or merging. Runs locally from the @liminallablibs/agent-guard-mcp npm package.

not rated 0 2mo ago A tokens not measured original MIT

veragent

2615

lixiaowww/veragent-mcp

MCP server Claude CodeCodexCursor +2

Veragent MCP server — check the trust/security score of MCP tools before installing them in Claude. Runs locally from the veragent-mcp Python package.

not rated 0 2mo ago A tokens not measured original MIT

fidacy-mcp

2616

fidacy/fidacy-open

MCP server Claude CodeCodexCursor +2

Action firewall for AI agents: blocks the wrong action before it runs, every verdict Ed25519-signed. Runs locally from the @fidacy/mcp npm package.

not rated 0 1mo ago A tokens not measured original Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: