Best Claude Code mcp servers for security on Agent (May 2026)

MCP Server to do dynamic AI SOC Security Threat analysis for a Text2SQL AI Agent.

Access specialized web3 AI agents for blockchain analysis, smart contract security auditing, token metrics evaluation, and on-chain interactions through the Heurist Mesh network. Provides comprehensive tools for DeFi analysis, NFT valuation, and transaction monitoring across mul…

Security-hardened NotebookLM MCP with post-quantum encryption (ML-KEM-768), GDPR/SOC2/CSSF compliance, and 14 security layers. Query Google's Gemini-grounded research from Claude and AI agents.

Framework for AI agents (Claude Code, Cursor, Codex, Gemini) to operate Google Ads, Meta Ads, and Search Console. Grounded in a local STRATEGY.md — not metric-chasing. Defense-in-depth security, local-first. Apache 2.0.

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.

Zero-knowledge password manager with MCP credential gateway. BIP-39 seed phrase recovery, deterministic passwords, policy-gated AI agent access (scope, rate limits, time windows, step-up approval), 70+ API key providers, and hash-chain audit trail. Go + Next.js + TypeScript.

Policy-based governance for AI agent tool calls. YAML policies, approval gates, risk assessment, and audit logging. Cross-platform: LangChain, OpenAI, Anthropic, MCP.

MCP audit server for agent discovery and certification. Provides trust and payment rail for AI agents including identity verification, escrow, settlement, and reputation management.

Trust intelligence for AI agents — identity stamps, reputation scoring (0-100), registry, forensic audit trails, and A2A passports via x402 micropayments.

Security-focused MCP server that provides safety guidelines and content analysis for AI agents.

Third-party certifying proxy — sign any HTTP call (AI agents, webhooks, microservices) with an independent Ed25519 signature, RFC 3161 timestamp, and Sigstore Rekor anchor. Works with Claude, GPT-4, Mistral, LangChain, AutoGen, or any HTTP client.

Deterministic AI safety policy engine with Z3 formal verification. Write, verify, and enforce machine-verifiable constraints for AI agents via MCP.

An MCP server that enables secure credential retrieval from 1Password to be used by Agentic AI.

A secure MCP (Model Context Protocol) server that enables AI agents to interact with the Authenticator App.

AI-safe secrets manager with MCP integration. Run commands with credentials injected as environment variables - AI agents never see plaintext secrets. Features output sanitization, AES-256-GCM encryption, and Argon2id key derivation.

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.

MCP server for domain and URL security analysis powered by GridinSoft Inspector, enabling AI agents to verify website and link safety.

Quantum-inspired keyring for AI coding agents. Secure secrets with superposition, entanglement, tunneling, and teleportation.

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.

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.

Verify AI agent communication protocols using session types. Formal specification with Lean 4 proofs, linter, formatter, and LSP. Catches deadlocks and role violations before deployment.

All-in-one security testing toolbox that brings together popular open source tools through a single MCP interface. Connected to an AI agent, it enables tasks like pentesting, bug bounty hunting, threat hunting, and more.

Free AI agent skill security scanner. Scan SKILL.md, MCP configs, and system prompts for credential theft, prompt injection, zero-width character attacks, and ClawHavoc indicators. Supports OpenClaw, Claude Code, Cursor, and Codex. No signup required.

Embeds Snyk's security engines into agentic workflows. Secures AI-generated code in real-time and accelerates the fixing vulnerability backlogs.

AI-agent admission-control MCP server: validates file edits against Ring 0 syntax + Ring 0.5 structural-cost regression + workspace boundary (path / glob / shell-redirect / symlink). Negative-space framing — emits BLOCK / WARN / PASS verdicts, never coaches the agent.

Policy enforcement for AI coding agents derived from existing instruction files (CLAUDE.md, .cursorrules, .windsurfrules, .github/copilot-instructions.md) — no separate YAML to maintain. Rules with prohibitive predicates (`never`, `forbids`, `must_not`) emit `permissionDecision:…

MCP server for AI agent for cybersecurity: automate assessment of documents, questionnaires & reports. Multi-format parsing, RAG knowledge base,Risks, compliance gaps, remediations.

Package Intelligence for AI agents. 22 tools across 17 ecosystems (npm/pypi/cargo/go/maven/nuget/rubygems/composer/pub/hex/swift/cocoapods/cpan/hackage/cran/conda/homebrew) — check health, vulnerabilities (OSV + CISA KEV + EPSS), typosquats, malicious flags, alternatives, known …