260 security MCP servers, most popular first. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| arai Enforces rules from existing agent instruction files (CLAUDE.md, .cursorrules) by blocking prohibited tool cal | 7 ★ | Low risk |
| mcp URL scanning and phishing triage: capture DOM snapshots, network requests and screenshots, and hunt historical | 7 ★ | Low risk |
| authbox Zero-knowledge password manager and MCP credential gateway: policy-gated agent access, deterministic passwords | 6 ★ | Low risk |
| guardvibe Security scanner for vibe-coded apps (Next.js, Supabase, Stripe, Prisma and more): taint analysis, auto-fix, S | 6 ★ | Low risk |
| mcp-server Query the RAD Security API for Kubernetes and cloud security findings, reports and runtime data. | 6 ★ | Review before installing |
| impri Self-hostable human-in-the-loop approval inbox: humans approve, reject or edit proposed agent actions via web, | 6 ★ | Review before installing |
| verify-mcp Offline verification of Ed25519/JCS-signed artifacts such as receipts, manifests and audit bundles. | 6 ★ | Low risk |
| lachesis Code property graph for C, Python and TypeScript: callers/callees, data and taint flow with source-to-sink wit | 6 ★ | Low risk |
| enigma-python-mcp Encrypt and decrypt messages with historically accurate Enigma machine emulators from the enigmapython library | 5 ★ | Low risk |
| AgentAvow Signed, recomputable safety scores for MCP servers, packages and tools, with offline-verifiable attestations a | 5 ★ | Low risk |
| mcp-firewall Deterministic security proxy for MCP that intercepts tool calls, enforces YAML policies, scans for secret leak | 5 ★ | Low risk |
| scalekit-mcp-server Manage Scalekit organizations, users and SSO. | 5 ★ | Review before installing |
| pci-dss-mcp PCI DSS static analysis for Go payment code: finds PAN/CVV exposure, weak crypto, missing audit logs and vulne | 5 ★ | Low risk |
| kepil Accountability layer for AI agents: per-version passports, per-job mandates with spending limits, a fail-close | 5 ★ | Low risk |
| cmdxray Offline safety gate for agent shell commands: rates each command as danger, caution or none and explains every | 5 ★ | Low risk |
| agent-passport-mcp Agent identity, scoped delegation and governance: issue passports, verify narrowing-only delegation chains, en | 4 ★ | Low risk |
| mcp-guardian Security and governance proxy for MCP with YAML policies (blocklists, rate limits, token budgets), token cost | 4 ★ | Low risk |
| anonymize-mcp Anonymize PII for GDPR in Czech and many other languages using ÚFAL/LINDAT NLP (MasKIT, NameTag), plus morphol | 4 ★ | Low risk |
| cyntrisec-cli Local-first AWS security analyzer that discovers attack paths and generates remediations using graph theory. | 4 ★ | Low risk |
| quantum_ring Quantum-inspired keyring for AI coding agents, securing secrets with superposition, entanglement, tunneling an | 4 ★ | Low risk |
| patch-tuesday-mcp Microsoft Patch Tuesday triage from the MSRC Security Update Guide: monthly rollups, CVE/KB lookups, supersede | 4 ★ | Review before installing |
| moltrust-mcp-server Trust infrastructure for AI agents: register DIDs, verify identities, query reputation scores, rate agents and | 4 ★ | Review before installing |
| thales-cdsp-cakm-mcp-server Thales CDSP CAKM integration for key management, cryptographic operations and compliance monitoring for Micros | 4 ★ | Review before installing |
| sast-mcp-server SAST/DAST scanners (Bandit, Semgrep, Trivy, CodeQL, OWASP ZAP and more) with closed-loop remediation, SARIF/SB | 4 ★ | Low risk |
| osv-ui Visual CVE audit dashboard for npm, Python, Go and Rust using OSV data, with browser-based human review and fi | 4 ★ | Low risk |
| qurl-mcp Mint, resolve, audit and rotate expiring, scope-limited access links (qURLs) via the qURL API. | 4 ★ | Low risk |
| VMware-Harden Read-only VMware vSphere compliance scanning and drift detection against CIS, vSphere SCG, China DJCP 2.0 and | 4 ★ | Low risk |
| mcp-pin Stdio proxy that pins every tool definition (name, description, input schema, annotations) when you approve a | 3 ★ | Low risk |
| shohei Infrastructure diagnostics: DNS checks, TLS certificate chain inspection, email security, global DNS propagati | 3 ★ | Low risk |
| solvitor-mcp Reverse engineering tools from Solvitor: extract IDL files from closed-source Solana smart contracts and decom | 3 ★ | Low risk |
| air-blackbox-mcp EU AI Act compliance scanner for Python AI agents (LangChain, CrewAI, AutoGen, OpenAI) with prompt injection d | 3 ★ | Low risk |
| inkog-mcp Audits agents and MCP servers for prompt injection, infinite loops, token bombing and missing human oversight, | 3 ★ | Low risk |
| rugsnare Pin MCP tool contracts by hash and catch silent drift, rug pulls and per-client bait-and-switch after approval | 3 ★ | Low risk |
| thales-cdsp-crdp-mcp-server Integration with the Thales CipherTrust Manager RESTful Data Protection service. | 3 ★ | Review before installing |
| ida-headless-mcp Headless IDA Pro binary analysis with concurrent sessions and Il2CppDumper and Blutter metadata import for Uni | 3 ★ | Low risk |
| calllint Offline pre-flight security linter for MCP servers, agent tools and skills that returns SAFE, REVIEW, BLOCK or | 3 ★ | Low risk |
| waxseal-sdk On-chain Ed25519 identity for AI agents: verify seals by fingerprint, validate document signatures and gate ir | 2 ★ | Low risk |
| horizon-shield Verify AI-agent evidence records on the Bitcoin-anchored JIDEC ledger: fetch record bytes, recompute the SHA-2 | 2 ★ | Low risk |
| mcp-bytesmith Offline byte toolbox: hex/Base64/Base58 encoding, cryptographic and CRC hashing, base conversion, secure token | 2 ★ | Low risk |
| spendshield Payment guardrails for AI agents: spend caps, budget and approval gates, prompt-injection defense, an encrypte | 2 ★ | Low risk |
| m2m-sentinel-sdk EVM bytecode capability analysis, EIP-1967 proxy resolution, gas recommendations and preflight safety checks f | 2 ★ | Low risk |
| privacyscrubber-mcp Local, zero-trust masking of PII and secrets. | 2 ★ | Low risk |
| intodns-mcp-server DNS and email security scans via IntoDNS.ai: SPF, DKIM, DMARC, DNSSEC, MTA-STS, BIMI, TLS, blacklist and deliv | 2 ★ | Low risk |
| honeylabs-mcp Honeypot threat intelligence from a sensor network: IP reputation, scanner classification, CVE probing trends | 2 ★ | Low risk |
| argus Query ARGUS-3 and check its status; WARDEN vets third-party MCP servers with a scored firewall, tool-definitio | 2 ★ | Low risk |
| agent-trust-stack-mcp Cryptographic provenance, blind reputation scoring and tamper-evident logging for agent interactions, with dis | 2 ★ | Low risk |
| trustboost-api Redacts emails, phone numbers, national IDs, private keys and financial data before text reaches LLMs, in Engl | 2 ★ | Low risk |
| chronoverify-mcp Verify a photo's capture time and provenance: C2PA Content Credentials validation, EXIF/XMP consistency checks | 2 ★ | Low risk |
| AgentValet Identity and credential broker for MCP servers: issues scoped, short-lived credentials per agent, with audit l | 2 ★ | Low risk |
| arc-gate-mcp Runtime governance for MCP tool calls that blocks prompt injection and capability abuse before tool results re | 2 ★ | Low risk |
| basedagents Agent identity registry (reputation, capability search, task marketplace, messaging) plus a local encrypted va | 2 ★ | Low risk |
| agentstamp Trust intelligence for AI agents: identity stamps, reputation scoring, a registry, forensic audit trails and A | 2 ★ | Low risk |
| jamjet-policy MCP interceptor that applies one YAML policy (block, require approval, audit, budget cap) to tool calls, also | 2 ★ | Low risk |
| arkforge-mcp Third-party certifying proxy that signs any HTTP call with an independent Ed25519 signature, RFC 3161 timestam | 2 ★ | Low risk |
| agentdevx-sdk Identity and credential gateway for agents: Ed25519 identity, encrypted credential vault, OPA policies with au | 2 ★ | Low risk |
| mint-mcp MINT Protocol work attestation for agents: cryptographically attest, verify, rate and discover agent work to b | 2 ★ | Low risk |
| lucairn-sdks Privacy gateway that sanitizes German and English PII before prompts reach an LLM and issues a signed, timesta | 2 ★ | Low risk |
| mcp-server Public data lookups: CVE/SBOM security audits, license compliance, patents, federal contracts, NPI providers, | 2 ★ | Low risk |
| claude-plugin Scan and fix a domain's email authentication (SPF, DMARC, DKIM, MX), blacklist status and domain/SSL expiry, w | 2 ★ | Low risk |
| taskbounty-check Local, read-only scanner for GitHub Actions and CI maintenance issues in AI-built apps, with finding explanati | 2 ★ | Low risk |
| fetch-guard URL fetcher and HTML-to-Markdown converter with layered prompt injection defense: hidden-element sanitization, | 2 ★ | Low risk |
| agentseal-mcp Action logs for AI agents: records every action in a SHA-256 hash chain as an audit trail. | 2 ★ | Low risk |
| mcp-keycloak-admin Administer Keycloak via its Admin REST API: users, roles, clients, groups, identity providers, federation and | 2 ★ | Low risk |
| mcp-shield Pre-install security scanner for MCP servers: detects backdoors, exfiltration code, obfuscation, dangerous exe | 2 ★ | Low risk |
| mcp-gatehouse Permission tiers, approval gates and secret-redacting audit logging enforced inside MCP servers at the tool bo | 2 ★ | Low risk |
| misp-mcp-server Read-only MISP threat intelligence (events, attributes, search, tags, feeds, galaxies) with prompt injection s | 2 ★ | Low risk |
| sicarius-guard Solana token safety oracle: byte-level SPL mint analysis, honeypot detection, freeze/mint authority checks, Bi | 2 ★ | Low risk |
| openterms-mcp Ed25519-signed consent receipts and a policy engine for agents: spending caps, action allowlists, escalation t | 2 ★ | Low risk |
| wrg-sigma-rules Write, validate and convert Sigma detection rules for Splunk, Elastic, Kibana and Wazuh, backed by a rule corp | 2 ★ | Review before installing |
| aggrete Policy proxy that refuses forbidden tool calls, stopping prompt-injection exfiltration and forbidden data comb | 2 ★ | Low risk |
| derbent One local gate for Claude Code, Codex, Copilot CLI and Antigravity: allow, deny and ask rules over MCP and bui | 1 ★ | Low risk |
| agentic-wallet-guardian-v3 Self-hosted security layer that evaluates AI agents' proposed blockchain transactions and returns an explainab | 1 ★ | Low risk |
| mcp-server-malcolm Malcolm threat hunting: search and aggregate network traffic, query Suricata alerts, browse Arkime sessions an | 1 ★ | Low risk |
| cyber-chef-mcp CyberChef MCP server providing 28 core data transformations, ciphers, hashing, JWT decoding, representation-ca | 1 ★ | Low risk |
| truecopy Supply-chain gate for agent skills and MCP servers: detects poisoned tool definitions, pins servers by hash, c | 1 ★ | Low risk |
| agentaegis-mcp Scan MCP servers and skills before install, vet endpoints before calling them, and run vulnerability scans, th | 1 ★ | Review before installing |
| dcl-webhook Deterministic audit layer that checks LLM and agent outputs against jailbreak, safety and trading compliance p | 1 ★ | Low risk |
| qiniso Verify IBAN, VAT, VIN, barcodes, national and tax IDs, crypto addresses, phone numbers, dates and holidays aga | 1 ★ | Low risk |
| dechonet-mcp Domain security checks: DNS, DNSSEC, TLS grading, HTTP security headers, SPF, DKIM and DMARC, port scans, ASN, | 1 ★ | Low risk |
| kakunin-mcp Agent compliance and identity: verify an agent's X.509 certificate scope, read its behavioral risk score and a | 1 ★ | Low risk |
| orihime Cross-repository code knowledge graph for Java, Kotlin, JavaScript and TypeScript: call-flow tracing, taint an | 1 ★ | Low risk |
| pod Least-privilege compiler for agents: record real tool calls, compile a minimal policy, enforce it at an MCP ga | 1 ★ | Low risk |
| aimarket-mcp SSRF-hardened web gateway with web fetch, web search and Metis verification, sharing an audited security core | 1 ★ | Low risk |
| unphurl-mcp URL security signals: redirects, brand impersonation, domain age, SSL validation, parked-domain detection, str | 1 ★ | Low risk |
| agentforge-trust-mcp Query AgentForge Trust Scores for MCP servers before connecting, covering security, code health, behavioral au | 1 ★ | Low risk |
| mcp Agent discovery and certification with a trust and payment rail: identity verification, escrow, settlement and | 1 ★ | Review before installing |
| shieldapi-mcp Security intelligence: HIBP password breach checks, email/domain/IP/URL reputation, prompt injection detection | 1 ★ | Low risk |
| web-exposure-mcp Read-only check of a live URL for publicly exposed secret files: .git, .env, JS source maps, backup/SQL dumps, | 1 ★ | Low risk |
| agentradar-mcp On-chain trust oracle for ERC-8004 and x402 agents: composite trust scoring, a scam wallet database, ERC-8004 | 1 ★ | Low risk |
| promptspeak-mcp-server Pre-execution governance for agent tool calls: risk classification, behavioral drift detection, a hold queue f | 1 ★ | Low risk |
| redact-pdf-mcp Permanently redact PII (names, emails, phone numbers, addresses, IBANs, card numbers) from PDFs, scans and scr | 1 ★ | Low risk |
| mcp-inspector Domain and URL security analysis with GridinSoft Inspector to verify website and link safety. | 1 ★ | Low risk |
| hejdar-mcp Runtime policy enforcement for AI agents: evaluate actions against organization policies before execution, in | 1 ★ | Review before installing |
| cleaner-code Locally scans AI-generated code for invisible Unicode, Trojan Source, homoglyphs, rules file backdoors and typ | 1 ★ | Low risk |
| ModelSafetyMCP Scan ML model artifacts, URLs and directories for unsafe serialization, malicious patterns and risky packaging | 1 ★ | Low risk |
| clawguard-mcp Security scanner for AI agents that detects prompt injections using regex patterns. | 1 ★ | Low risk |
| securecode-mcp Encrypted secrets vault for Claude Code that injects secrets into local files so the AI never sees raw values, | 1 ★ | Low risk |
| secobserve-mcp SecObserve vulnerability and license management: triage observations, manage products and rules, import scan r | 1 ★ | Review before installing |
| mcp-shield Static security scanner for MCP servers and agent tools: detects secrets, shell execution, risky tool descript | 1 ★ | Low risk |
| pentagonal Generate, audit, fix and compile smart contracts on Ethereum, Solana, Base and other chains, with adversarial | 1 ★ | Low risk |