Search: ai-security
Search MCP servers and agent skills by name, description, category or topic — 24 results.
mariocandela/beelzebub
Beelzebub is a honeypot framework that lets you build honeypot tools using MCP. Its purpose is to detect prompt injection or malicious agent behavior. The underlying idea is to provide the agent with tools it would never use in its normal work.
KryptosAI/mcp-observatory
Regression testing for MCP servers. Auto-discovers servers from Claude configs, checks capabilities, invokes tools, detects schema drift between versions, and recommends new servers based on your environment. Works as both a CLI and an MCP server.
arian-gogani/nobulex
Proof-of-behavior enforcement for AI agents. Define behavioral covenant rules (permit/forbid/require), enforce at runtime before execution, get SHA-256 hash-chained tamper-evident audit logs, and verify compliance independently. Cross-agent verification handshake — no proof, no transaction. MIT licensed, 4,244 tests.
Synvoya/codeinspectus
Local-first, zero-egress security scanner for AI-generated / "vibe-coded" JS/TS. Bundles Opengrep, Gitleaks & Trivy behind one CWE-keyed schema and adds AI-code-specific checks (client-side secret exposure, Supabase RLS, prompt-injection & LLM-output XSS sinks). No account, no telemetry.
UPinar/contrastapi
Security intelligence API with 31 MCP tools for CVE/EPSS/KEV lookup, domain recon (DNS/WHOIS/SSL/subdomains/CT logs), IOC/threat intel, OSINT (email/phone/username), and code security scanning (secrets, injection). Free 100 req/hr.
msaad00/agent-bom
AI supply chain security scanner with 18 MCP tools. Auto-discovers 20 MCP clients, scans dependencies for CVEs (OSV/NVD/EPSS/CISA KEV), maps blast radius from vulnerabilities to exposed credentials and tools, runs CIS benchmarks, generates CycloneDX/SPDX SBOMs, and enforces compliance across OWASP LLM Top 10, MITRE ATLAS, NIST AI RMF, and EU AI Act.
jnMetaCode/shellward
AI Agent Security Middleware & MCP Server with 8-layer defense including prompt injection detection, DLP data flow tracking, command blocking, and PII detection. 7 MCP tools, zero dependencies.
mastyf-ai/mastyf.ai
Open-source runtime security proxy for MCP. Transparently intercepts every tools/call through an 18-class attack defense pipeline (prompt injection, SSRF, shell injection, SQL injection, credential exfil, polyglot attacks) with a YAML policy engine and 304-entry adversarial corpus. Trust scoring for npm MCP packages with 0-100 badges. Cloud dashboard, Docker image, Python SDK. MIT.
sgateway/s-gw
Local credential approval and execution gateway for AI coding agents. Agents receive typed handles instead of raw API tokens, SSH keys, and cloud credentials; one-time approvals bind the credential, command, arguments, working directory, environment bindings, and target. Injects credentials only into the approved child process, sanitizes output, and records a local audit trail. Install with `npm i
Arun-kc/schemabrain
Read-only trust layer for Postgres: the agent never writes SQL — twelve tools compile it from definitions you control, PII and secret categories are refused before the query runs, and every call lands in a tamper-evident SHA-256 audit chain.
Rul1an/assay
Policy-as-code gate for MCP. A fail-closed proxy that denies risky tool calls before they run, produces offline-verifiable evidence bundles of what executed, and enforces IPv4/TCP egress in-kernel via eBPF/LSM and Landlock on Linux. Deterministic and offline-first.
tomjwxf/scopeblind-gateway
Security gateway that wraps any MCP server with per-tool policies, approval gates, and optional Ed25519-signed receipts. Shadow mode logs every tool call; enforce mode blocks, rate-limits, or requires approval.
emiliaprotocol/emilia-protocol
Human sign-off + trust receipts for AI agents: requires a named human's approval before an irreversible action (payment release, record change, deploy), then mints an offline-verifiable Ed25519 Trust Receipt. Also exposes trust profiles, receipt verification, disputes, and delegation. Apache-2.0; policy engine formally verified. Install: `npx -y @emilia-protocol/mcp-server`.
ScopeBlind/verify-mcp
Offline verification of signed artifacts -- receipts, manifests, audit bundles. Ed25519 + JCS. No accounts, no API calls. Apache-2.0.
goklab/guardvibe
Security MCP for vibe coding with 330 rules and 29 tools. Purpose-built for AI-generated code — scans Next.js, Supabase, Clerk, Stripe, Prisma, Hono, GraphQL, and 25+ modules. Cross-file taint analysis, host security audit, auto-fix, SARIF export, pre-commit hook, and CVE version detection. Zero config, runs locally.
Acacian/aegis
Policy-based governance for AI agent tool calls. YAML policies, approval gates, risk assessment, and audit logging. Cross-platform: LangChain, OpenAI, Anthropic, MCP.
calllint/calllint
Pre-flight security linter for MCP servers, agent tools, and skills. Scans a config *before* it runs — offline, deterministic, evidence-backed — and returns SAFE / REVIEW / BLOCK / UNKNOWN verdicts without executing the server it judges. CLI (`npx calllint scan`), MCP server (`npx calllint-mcp`), SARIF + CI gate. UNKNOWN is never SAFE.
sentien-labs/verdictswarm-mcp
Multi-AI crypto token scanner. 6 AI agents independently analyze and debate token risk on Solana, Base, and Ethereum. Detects rug pulls, honeypots, holder concentration, and wash trading through adversarial consensus.
joergmichno/clawguard-mcp
Security scanner for AI agents that detects prompt injections using 42+ regex patterns
82ch/MCP-Dandan
Real-time security framework for MCP servers that detects and blocks malicious AI agent behavior by analyzing tool call patterns and intent across multiple threat detection engines.
ppcvote/misp-mcp-server
MISP (Malware Information Sharing Platform) MCP server with built-in prompt injection defense via [prompt-defense-audit](https://github.com/ppcvote/prompt-defense-audit). 8 read-only threat-intel tools (events, attributes, search, tags, feeds, galaxies). Scans every MISP response for adversarial seeding before returning to LLM. Tracks [MISP/MISP#10745](https://github.com/MISP/MISP/issues/10745). M
goldmembrane/cleaner-code
AI code security scanner MCP server. Detects 9 categories of threats in AI-generated code (invisible Unicode, Trojan Source, homoglyphs, Glassworm steganography, rules file backdoors, dependency typosquatting, obfuscation) using static analysis plus CodeBERT deep learning. Runs locally, free tier.
getaegis/aegis
Credential isolation proxy for AI agents. Injects secrets at the network boundary with domain restrictions, agent authentication, and audit logging. No SDK required — works as a transparent HTTP proxy or MCP server.
9hannahnine-jpg/arc-gate-mcp
Runtime governance for MCP tool calls. Blocks prompt injection and capability abuse before tool results reach your agent.