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 server Claude CodeCodexCursor +2
EUDI Wallet MCP — EU Digital Identity Wallet under eIDAS 2.0 for AI agent authentication. ISO 18013-5 (mDoc) + W3C VC 2.0 + OID4VC + OID4VP. By MEOK AI Labs. Runs locally from the eudi-wallet-mcp Python package.
CSOAI-ORG/firmware-attestation-mcp
MCP server Claude CodeCodexCursor +2
Firmware Attestation MCP — hardware trust layer for sovereign AI. Scan firmware, check NSA-ANT-class persistence indicators (BIOS/SMM/HPA/boot-ROM), HMAC-signed firmware attestation, gate AI inference on verified hardware trust. Runs locally from the firmware-attestation-mcp Python package.
CSOAI-ORG/iso-42005-impact-mcp
MCP server Claude CodeCodexCursor +2
ISO/IEC 42005:2025 AI Impact Assessment MCP — runs full lifecycle impact assessment across 6 phases × 7 impact categories. Cross-walks to EU AI Act + ISO 42001. By MEOK AI Labs. Runs locally from the iso-42005-impact-mcp Python package.
CSOAI-ORG/csoai-cra-annex-iv-classifier-mcp
MCP server Claude CodeCodexCursor +2
EU Cyber Resilience Act product classifier MCP. Classifies PDEs into CRA hierarchy (default / Class I / Class II / Annex IV per Implementing Reg 2025/2392), audits the 15 Annex I cybersecurity requirements, generates Annex VIII technical docs skeleton, emits HMAC-signed classification certs. Built for 11 Dec 2027…
MCP server Claude CodeCodexCursor +2
OWASP Top 10 for AI Agents security assessment tools. Capabilities: full agent security scan, prompt injection detection, tool poisoning check, excessive agency, data leakage. Built by MEOK AI Labs. Runs locally from the owasp-agentic-mcp Python package.
Skill Claude CodeCodex
Scan a public GitHub MCP-server repository for security issues before installing or connecting to it. Calls the hosted compuute-scan API at scan.compuute.se and returns severity counts, a 0-100 score, the most severe findings, and an honest triage disclaimer. Use BEFORE recommending or installing an unfamiliar MCP…
Creed-Space/creedspace-mcp-server
MCP server Claude CodeCodexCursor +2
Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication. Runs locally from the @creedspace/mcp-server npm package.
DevInder1/supply-chain-scanner-public
Cursor rule Cursor
TridentChain Security — supply-chain vulnerability scanning for this workspace.
MCP server Claude CodeCodexCursor +2
Local, privacy-preserving PII toolkit over MCP — the model reasons on shape, deterministic local code touches substance, only masked results return. Runs locally from the obsify Python package.
MCP server Claude CodeCodexCursor +2
Email-domain intelligence: MX capability, provider, disposable status, SPF, DMARC, and MTA-STS. Remote server at mailtype-api.onrender.com.
MCP server Claude CodeCodexCursor +2
Free passive security scanning - check any domain's DMARC, TLS, headers, and exposures. Runs locally from the nel-veil-mcp npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Verifies Ed25519-signed attestation records and builds audit reports via MCP tools. Runs locally from the paceproof-cli npm package.
MCP server Claude CodeCodexCursor +2
Verify that a GitHub issue closed as "fixed" actually has a merged fix. Catches security issues marked fixed whose PR was never merged. Runs locally from the shimguard-cli Python package.
MCP server Claude CodeCodexCursor +2
PyPI wrapper for TenantGuard, a tenant-isolation security-audit CLI for self-hosted multi-tenant AI-agent platforms. Downloads and runs the official prebuilt Go binary from GitHub Releases, Sigstore-verified on first run. Runs locally from the tenantguard-cli Python package.
MCP server Claude CodeCodexCursor +2
Tamper-evident attestation tools for AI agents — on-chain receipts on Hedera Hashgraph mainnet. Runs locally from the @cryptair/mcp-server npm package. Needs 3 environment variables to run.
Skill Claude CodeCodex
Use this skill when the user is building, securing, or auditing a browser-based AI agent (Playwright, Puppeteer, Stagehand, browser-use, or custom browser automation). Triggers on requests to "secure my browser agent", "detect prompt injection in web pages", "block my agent from visiting bad URLs", "scan this page for…
UnbearableDev/dockerfile-audit
MCP server Claude CodeCodexCursor +2
Hadolint-grade Dockerfile audit — 19 checks: secrets, privileges, supply chain, hygiene. Remote server at unbearable-dev--dockerfile-audit.apify.actor.
UnbearableDev/docker-compose-audit
MCP server Claude CodeCodexCursor +2
Security audit for docker-compose.yml — 25 checks: secrets, privileges, network, volumes, images. Remote server at unbearable-dev--docker-compose-audit.apify.actor.
UnbearableDev/github-actions-audit
MCP server Claude CodeCodexCursor +2
GitHub Actions workflow security audit - 21 checks: pinning, permissions, secrets, injection. Remote server at unbearable-dev--github-actions-audit.apify.actor.
MCP server Claude CodeCodexCursor +2
Four IaC audits in one call: Compose, Dockerfile, GitHub Actions, Kubernetes. 131 checks. Remote server at unbearable-dev--iac-audit-pack.apify.actor.
UnbearableDev/k8s-manifest-audit
MCP server Claude CodeCodexCursor +2
MCP server "k8s-manifest-audit", hosted remotely at unbearable-dev--k8s-manifest-audit.apify.actor, as configured in UnbearableDev/k8s-manifest-audit.
MCP server Claude CodeCodexCursor +2
WHOIS, DNS, SSL, and domain availability lookups for AI assistants. Runs locally from the @whoisjson/mcp-server npm package. Needs 1 environment variable to run.
ai-supply-store/ai-supply-plugin
Plugin Claude Code
Bundles 1 skill, 2 commands, 1 MCP server · 69 tokens together
Discover, install, publish and review security-scanned AI capabilities (MCP servers, skills, agents, datasets, guardrails, evals) from ai-supply.store — without leaving Claude.
andrewszk/clawvault-mcp-server
MCP server Claude CodeCodexCursor +2
AI agent payment security - spending limits, whitelists, and human approval. Runs locally from the clawvault-mcp-server npm package. Needs 1 environment variable to run.
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: