Security MCP servers

Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.

Search the Russian software registry for import-substitution and FSTEC/FSB-certified products, with full-text search and manufacturer listings.

Detect and redact PII, PHI, PCI and secrets in text and files before an AI agent sees them.

Supply-chain malware scanner and MCP server: vet packages in 15 ecosystems before install, offline.

Webmin Linux system administration: services, users, storage, security, databases and more.

Security scanner for vibe-coded apps (Next.js, Supabase, Stripe, Prisma and more): taint analysis, auto-fix, SARIF export, pre-commit hook and CVE detection.

Build and run a backend on the Anythink platform: relational data with row-level security, search, RBAC, workflows, growth and retention tools, and payments.

74 paid web-analysis APIs (SEO, security, TLS, DNS, email) as MCP tools. USDC via x402.

Interact with the RAD Security platform which provides AI-powered security insights for Kubernetes and cloud environments.

Minimal MCP server for scanner capture (ADF/duplex/page-size); typed tools; JSON Schema–validated I/O; multipage assembly; Node 22 + SANE.

Zero-knowledge password manager and MCP credential gateway: policy-gated agent access, deterministic passwords, BIP-39 recovery and a hash-chain audit trail.

An MCP server that provides access to FedRAMP 20x security requirements and controls.

Local-first defensive scanner for vulnerable dependencies, leaked secrets, and risky agent configs

Secure grip for your agent's secrets - security-hardened MCP gateway with proxy token architecture

French public services: tax, property, admin, education, healthcare, security, risks, legal texts

MCP server: static security scanner for MCP servers, agent skills & plugins. 17 attack patterns.

Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.

Offline verification of Ed25519/JCS-signed artifacts such as receipts, manifests and audit bundles.

Argus — the QA layer for AI-assisted development. Claude-native (MCP) Chrome audits across 67 categories — errors, visual regressions, a11y, security, performance — no test files, secrets redacted by default (Aegis).

Drive your logged-in Chrome via an extension: compact element refs, visual regression, accessibility, SEO and security audits, and network mocking.

Anonymize PII for GDPR in Czech and many other languages using ÚFAL/LINDAT NLP (MasKIT, NameTag), plus morphology, translation and spellcheck.

Deterministic guardrail for AI-written diffs: AST-based checks for SQLi, SSRF, XXE, hardcoded secrets and over-abstraction, scoped to the changed lines.

Self-hostable human-in-the-loop approval inbox: humans approve, reject or edit proposed agent actions via web, mobile, Slack, Discord or Telegram.

Accountability layer for AI agents: per-version passports, per-job mandates with spending limits, a fail-closed action gate and a hash-chained journal.

Code property graph for C, Python and TypeScript: callers/callees, data and taint flow with source-to-sink witnesses, points-to and guard/sink structure.

PCI DSS static analysis for Go payment code: finds PAN/CVV exposure, weak crypto, missing audit logs and vulnerable deps, each mapped to a PCI requirement.

Website audits: SEO, security headers and SSL, Lighthouse performance, broken links, WCAG accessibility, Schema.org validation, competitor gaps and robots.txt.

Offline safety gate for agent shell commands: rates each command as danger, caution or none and explains every flag, pipe, redirect and subshell.

Deterministic security proxy for MCP that intercepts tool calls, enforces YAML policies, scans for secret leakage and logs everything.

Signed, recomputable safety scores for MCP servers, packages and tools, with offline-verifiable attestations and a GitHub Action to gate CI merges.

Context-aware secret scanner: lets an AI agent scan, verify, and rewrite secrets before committing.

MCP server for MariaDB. Read-only by default, row caps, timeouts, secrets never logged.

MCP server for MySQL. Read-only by default, row caps, statement timeouts, secrets never logged.

PhoneInfoga - International Phone Number OSINT

MCP server for PostgreSQL. Read-only by default, row caps, timeouts, secrets never logged.

MCP server for Proofpoint TAP — threat intelligence, forensics, quarantine, and email security.

MCP server for Proofpoint TAP — threat intelligence, forensics, quarantine, and email security.

Manage Scalekit organizations, users and SSO.

Read-only access to secrets in a local KeePassXC vault. Runs commands with them injected.

Security and governance proxy for MCP with YAML policies (blocklists, rate limits, token budgets), token cost tracking, health monitoring and RBAC.

Local-first AWS security analyzer that discovers attack paths and generates remediations using graph theory.

Official MCP server for IP geolocation, IP security, abuse contacts, ASN, timezone, astronomy, and user-agent parsing.

Malcolm threat hunting: search and aggregate network traffic, query Suricata alerts, browse Arkime sessions and resolve NetBox assets. Read-only by default.

Trust infrastructure for AI agents: register DIDs, verify identities, query reputation scores, rate agents and manage W3C Verifiable Credentials.

Microsoft Patch Tuesday triage from the MSRC Security Update Guide: monthly rollups, CVE/KB lookups, supersedence chains and EPSS/CISA KEV urgency ranking.

SAST/DAST scanners (Bandit, Semgrep, Trivy, CodeQL, OWASP ZAP and more) with closed-loop remediation, SARIF/SBOM/VEX export and compliance reporting.

Read-only VMware vSphere compliance scanning and drift detection against CIS, vSphere SCG, China DJCP 2.0 and PCI-DSS, with remediation suggestions.

VMware NSX security: Distributed Firewall policies and rules, security groups, Traceflow troubleshooting and IDS/IPS profiles, with checks before deletion.