Best Security MCP servers

SSH server management for agents, with per-server read-only and allowlist security modes

Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.

Deterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.

Butterbase MCP server — manage your backend: schemas, auth, functions, storage, RAG, deploys.

Dead code, security, secrets detection and code quality for Python, TypeScript, Go.

Commerce preflights, Walmart mappings, D365 authorization, and offer checks; no external writes.

Authorize consequential AI agent actions before execution

AI agent identity, signed credentials, delegated authority and governance evidence.

Exact-action approval for consequential agent actions: request, track, and verify signed receipts.

AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.

Local, deterministic review of Git changes: weakened tests and CI gates, risky flows, blast radius.

MCP server bridging Claude.ai/Desktop with self-hosted OpenClaw via OAuth 2.1.

Deterministic security layer your AI can't be. 589 rules, 39 tools, CLI + doctor + host audit.

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

Server security audit (413 checks), hardening, and fleet management across 4 cloud providers.

Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.

Read, write and scan process memory, Cheat Engine style, on Windows, Linux and macOS.

MCP security scanner. CI-native testing, attack simulation, health scoring, and SARIF.

Value-blind secret metadata and gated workflows for AI coding agents through Phantom's local proxy.

Security-first MCP server for reverse engineering, malware analysis, forensics, and SAST.

Evidence-backed AppSec for AI applications and agents. Powered by HAIEC.

Static analysis scanner for MCP server code and multi-tenant SaaS applications.

MCP server for Shodan API — device search, IP and domain recon, DNS, and CVE/CPE queries.

MCP server for querying VirusTotal API with comprehensive security analysis tools.

MCP server for the SCF Controls Platform — 187 tools for controls, evidence, risk, and TPRM.

Wallet auth: send a wallet and conditions, get a signed boolean across 37 chains.

Email MCP server for Gmail, Outlook and any IMAP mailbox, hardened against prompt injection

Professional network analysis with tshark. Security audits, deep-dives, and threat detection.

Network scanner for AI agents: discover hosts, scan TCP and UDP ports, query DNS and mDNS.

Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.

Scan prompts, tool definitions and model output for injection, and guard agent tool calls.

IP geolocation, security, ASN, abuse, time zones, astronomy, and user-agent parsing over stdio.

Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.

AWS security scanner with attack chain detection, IAM privilege escalation, and fixes

Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.

Read-only Polymarket data tools for AI agents: profiles, PnL, market scans. No keys, no orders.

Protected RAG storage — agents discover public metadata, content only by access token.

Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.

Search-first MCP server for JavaScript reverse engineering: 735 tools across 36 domains.

Local-first memory for AI agents that reaches backward to find a failure's root cause.

Read-only codebase audits for coding agents: secrets, RLS, deps, review verdicts. No writes.

Read-only Postgres/Supabase RLS audit with a rolled-back probe that proves who can read which rows.

MCP server for dnstwist: detect typosquatting, phishing and brand impersonation domains.

React Native and Expo health check: upgrade blockers, store rules, crash risks, security findings

Reliability + security proxy for MCP: runtime tool-security and a compliance-mapped audit trail.

Local-first supply-chain security gate for npm/pnpm/bun: typosquat, release age, provenance checks

Static preflight safety gate for MCP servers — scan configs before you run them. Never executes.

A security-focused MCP server for self-hosted n8n Community Edition.

Security scanner and graph for agentic infrastructure — agents, MCP, runtime, and blast radius.

Production readiness for vibe-coded apps. 52 checks for security, reliability, and performance.

Agentic job hunt: scan careers pages, score against your resume, draft applications. Never applies.

CVE, KEV, EPSS, SBOM and advisory lookups; per-CVE exposure from Shodan data (© Shodan). Keyless.

PDF MCP: generate PDF/A & PDF/X-4, sign & verify PAdES (LTV), forms, merge, split, encrypt. 28 tools

ISO 27001 compliance workspace for Claude. Risks, policies, SoA, evidence, and audit workflows.

Save and use 1Password secrets locally without exposing plaintext to AI agents.

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

Easily find and fix security issues in your applications leveraging Snyk platform capabilities.

Point Gecko at an OpenAPI spec; get first-call-correct, auth-hidden agent tools.

Present PDFs from the browser: upload to start a slideshow or validate Presio sidecars. No auth.

Open-source MCP server: encrypted local keys and state, operator approval gates, a hash-chained log.

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

AI-native ERP MCP: ES/EU fiscal compliance (VeriFactu/TicketBAI/Facturae), invoicing, tax, banking

Pin MCP tool contracts by sha-256; catch silent drift, rug pulls and bait-and-switch in CI.

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

Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.

Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.

Provenance gateway for stdio MCP servers: blocks tool calls fed by untrusted tool results.

Chemical safety intelligence — 24 tools: compatibility, hazards, PPE, compliance, SDS lookup

Keep credentials out of AI coding agents with local approvals, scoped injection, and audit trails.

SQL-native query and provisioning engine for cloud infrastructure, served over MCP.

Input firewall for AI agents: scan text and files before an agent reads them. Local, no network.

Provenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.

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

iptables for MCP — blocks dangerous tool calls, scans for secrets, logs everything.

Manage Meta apps: creation, configuration, webhooks, permissions, compliance, and App Review.

Verify AI answers and executions and seal signed, offline-verifiable evidence records.

Technology intelligence feed for AI agents: tech stack, compliance, security.

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

Public-record corpus of AI litigation, regulation, and enforcement, anchored to EveryAILaw.

Git-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.

Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.

Authorization-gated MCP server to discover and run 670+ security tools for CTF, pentest, and DFIR.

Passive security scanner: audits MCP servers against the OWASP MCP Top 10, graded A-F.

Offline TrustLint checks: EU AI Act Article 5, Article 50, GPAI, plus GDPR and HIPAA.

Scan Solana/Anchor code against the Solana Security Standard and serve the ruleset to MCP clients.

MCP server for running Ox Security MegaLinter via mega-linter-runner

Check if an MCP server's tool definitions changed after approval, from a signed public log.

Security-hardened NotebookLM MCP with post-quantum encryption

Final release; the checks moved to 9lives (9l mcp). Local QA MCP: scan, inspect, repro, run tests.

Journals every MCP tool call with secrets redacted; with a policy, holds risky calls for approval

Pre-deploy security auditor for AI agent code — the risks generic SAST misses.

Safe, self-hosted ZAP operator for guided AI security scans and reports.

MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.

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

Offline AI governance code indicators (EU AI Act, Korea, Colorado). Indication, not legal advice.

Check, test, prove and review a rowstile policy: access rules for Postgres row-level security

Scan, enumerate, and risk-score every MCP server configured on your machine.

VMware compliance scanning (CIS, vSphere SCG, GB/T 22239, PCI-DSS) with drift detection.

Guardian layer for AI agents: identity, secrets, audit via MCP.

AI governance MCP server: trust scoring, guardrails, bias/hallucination detection, compliance.

Local-first MCP security scanner and CLI for AI-generated applications.

CLI tool and MCP server that tests MCP servers for spec compliance

Read-first Redis MCP: SCAN key explorer, keyspace/TTL/memory/slowlog stats, DBA advisor

Guardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant isolation

EU AI Act + GDPR compliance scanner. One call, no arguments, 10 seconds. 22 AI frameworks detected.

MCP server for Kalshi prediction markets: native RSA-PSS auth, rate limiting, demo/prod safety.

Catches hallucinated and slopsquatted npm and PyPI packages before an agent installs them.

Mask PII in outbound MCP tool-call arguments, unmask the results. Indian identifiers included.

Runtime proxy for MCP security, cost governance & audit

Audit MCP servers for tool poisoning, rug pulls and supply-chain risk (OWASP MCP Top 10).

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

Open bounty protocol for AI agents. 22 tools: token safety scans + paid missions. 0.5% fee.

Scans Greenhouse, Lever, Ashby, Workday, Rippling for roles in any category. Clay-ready.

Answers EU Digital Product Passport questions: scope, required fields, registry and law changes.

Verify consequential AI actions before they execute.

Scans MCP servers for prompt injection, data exfiltration, and privilege escalation.

Contract Review Ai MCP Server by MEOK AI Labs

Answer CTRLRun approvals from an MCP client: list what is held, inspect it, grant or deny.

Local-first privacy MCP server for sensitive AI workflows

Guard Core security MCP: SecurityConfig validation, docs search, live threat detection.