Security MCP servers

Control plane MCP that dedups scanner output, rate-limits hosts, and runs non-destructive proofs.

AI-powered Kubernetes diagnostics, RBAC analysis, security checks, and app deployment via MCP

Scan installed MCP servers for security vulnerabilities with 16 detection engines.

Read-only MISP threat intelligence (events, attributes, search, tags, feeds, galaxies) with prompt injection scanning of every response.

Security-first MySQL MCP server with AST validation, table whitelist, schema resources, and audit.

Ed25519-signed consent receipts and a policy engine for agents: spending caps, action allowlists, escalation thresholds and JWKS-backed provider verification.

SupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.

Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.

AI-driven penetration testing - 22 security tools behind safety-hardened MCP endpoints

MCP server teaching AI agents to implement TideCloak: auth, E2EE, IGA, security analysis

Read-only CVE intelligence, remediation playbooks, and agent setup guides. Not a scanner.

Zero-trust MCP security proxy with policy enforcement, PII scrubbing, approvals, and audit trails.

Security scanner for MCP servers. Find vulnerabilities before your AI agent does.

Pre-install security scanner for MCP servers: detects backdoors, exfiltration code, obfuscation, dangerous execution, prompt injection and supply chain risks.

MCP interceptor that applies one YAML policy (block, require approval, audit, budget cap) to tool calls, also usable in Claude Code hooks and agent SDKs.

Solana token safety oracle: byte-level SPL mint analysis, honeypot detection, freeze/mint authority checks, Birdeye market data and composite risk scoring.

Scaffold Starter Series projects and check release, deployment, security, and agent instructions.

Generate API test cases from Swagger/OpenAPI specs (auth, validation, boundary, security and more) and export them to Gherkin, Postman, k6, pytest or TestRail.

Open Korean e-Gov and finance sites in a clean, disposable Windows Sandbox with security programs.

Detects leaked secrets (API keys, tokens, private keys) in source code.

Redacts emails, phone numbers, national IDs, private keys and financial data before text reaches LLMs, in English, Spanish, Portuguese, German and Japanese.

Scans code, IaC and AI-agent config for security problems. Read-only — nothing can be edited.

Write, validate and convert Sigma detection rules for Splunk, Elastic, Kibana and Wazuh, backed by a rule corpus covering MITRE ATT&CK tactics.

Threat intelligence: enrich IOCs (IP, domain, URL, hash), search CVEs and actors, scan SBOMs.

npm registry MCP server — package intelligence, security audits, dependency analysis

Security trust layer that monitors MCP packages on npm for install scripts, command injection, hardcoded secrets, capability drift and publisher posture.

Locally scans AI-generated code for invisible Unicode, Trojan Source, homoglyphs, rules file backdoors and typosquatting using static analysis and CodeBERT.

Scores MCP servers, AI skills and npm packages before install, scanning for prompt injection, credential theft and supply-chain risk, with a go/no-go gate.

Pre-execution governance for agent tool calls: risk classification, behavioral drift detection, a hold queue for dangerous operations and an audit trail.

SEO and GEO (AI search) analysis: Core Web Vitals, structured data, security headers, mobile SEO, image audits, internal linking and AI crawler access.

Permanently redact PII (names, emails, phone numbers, addresses, IBANs, card numbers) from PDFs, scans and screenshots, with multilingual OCR.

Query ARGUS-3 and check its status; WARDEN vets third-party MCP servers with a scored firewall, tool-definition pinning and drift detection.

WCAG 2.1 AA accessibility scanner (Playwright + axe-core) with grounded, browser-verified fixes. MCP server for Claude Code and any MCP client; also a Claude Code plugin.

Scan MCP servers and skills before install, vet endpoints before calling them, and run vulnerability scans, threat intel and compliance checks.

Self-hosted security layer that evaluates AI agents' proposed blockchain transactions and returns an explainable allow, warn or block decision.

On-chain trust oracle for ERC-8004 and x402 agents: composite trust scoring, a scam wallet database, ERC-8004 identity lookup and EAS attestations on Base.

Policy proxy that refuses forbidden tool calls, stopping prompt-injection exfiltration and forbidden data combinations across Slack, Drive, GitHub and more.

Agent discovery and certification with a trust and payment rail: identity verification, escrow, settlement and reputation management.

SSRF-hardened web gateway with web fetch, web search and Metis verification, sharing an audited security core with Metis and ARGUS.

Arcwall Security MCP server for Claude Code, Cursor, Windsurf and any MCP-compatible AI coding tool

MCP server for the BeVigil OSINT API — mobile app attack surface discovery (hosts, subdomains, S3 buckets, wordlists) for AI agents

Middleware that gates MCP tool calls behind a Hashcash proof-of-work challenge or an L402 Lightning payment via self-hosted LNbits.

Deterministic audit layer that checks LLM and agent outputs against jailbreak, safety and trading compliance policies and logs verdicts to a hash chain.

Domain security checks: DNS, DNSSEC, TLS grading, HTTP security headers, SPF, DKIM and DMARC, port scans, ASN, RDAP and WHOIS, plus an overall health score.

Demand-signal scanner for validating product and dev-tool ideas using GitHub repo signals, Hacker News attention and npm/PyPI download counts.

One local gate for Claude Code, Codex, Copilot CLI and Antigravity: allow, deny and ask rules over MCP and built-in tool calls, approvals from a terminal UI, and hash-chained receipts.

Everstake non-custodial staking data across many networks: live APY, uptime metrics, rewards calculator, integrations, security and compliance info.

Discover, invoke and verify agents on a paid marketplace: code generation, security scanning (OSV.dev, GitGuardian) and lead scoring, with signed results.