260 security MCP servers, most popular first. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| privacyfence Privacy and approval gateway between AI assistants and Gmail, Drive, Slack, Salesforce, Jira and more: human a | 1 ★ | Low risk |
| SecureAudit-MCP Static C/C++ memory-safety scanning and PE/ELF binary protection audits (ASLR, DEP/NX, SafeSEH, PIE), with rem | 1 ★ | Low risk |
| dawshund_mcp Enumerate AWS IAM data, analyze effective permissions and visualize access relationships across users, roles a | 1 ★ | Low risk |
| scamverify-mcp Scam and threat checks for phone numbers, URLs, texts, emails, documents and QR codes using FTC/FCC complaints | 1 ★ | Low risk |
| agentscore-mcp-server Security trust layer that monitors MCP packages on npm for install scripts, command injection, hardcoded secre | 1 ★ | Review before installing |
| algenta-sdk Algenta decision engine: dataset discovery, exact queries, utility models, decision memory and governed agent | 1 ★ | Review before installing |
| skillssafe-mcp Scan SKILL.md files, MCP configs and system prompts for credential theft, prompt injection, zero-width charact | 1 ★ | Low risk |
| aegis Admission control for agent file edits: checks syntax, structural-cost regressions and workspace boundaries, r | 1 ★ | Low risk |
| hvtracker-mcp Pre-connect supply-chain trust checks for AI agents, frameworks and MCP servers: evidence-based HVTrust scores | 1 ★ | Low risk |
| captcha-mcp Middleware that gates MCP tool calls behind a Hashcash proof-of-work challenge or an L402 Lightning payment vi | 1 ★ | Low risk |
| mcp-regulated-ai-compliance Regulated-industry AI compliance knowledge: control lookup, use-case classification and crosswalks for EU AI A | 1 ★ | Low risk |
| volta-mcp-server Burn-after-read encrypted Volta Notes for agents: hand off credentials between users and agents without secret | 1 ★ | Low risk |
| proofport-ai Generate zero-knowledge proofs of identity claims (Coinbase KYC, country, Google OIDC, Microsoft 365) without | 1 ★ | Low risk |
| depscope Package intelligence across many ecosystems: health, vulnerabilities (OSV, CISA KEV, EPSS), typosquats, malici | 1 ★ | Low risk |
| vaulted-mcp-server Share end-to-end encrypted, self-destructing secrets from an agent, reading them from env vars or files so the | 1 ★ | Low risk |
| mcpskills-server Scores MCP servers, AI skills and npm packages before install, scanning for prompt injection, credential theft | 1 ★ | Low risk |
| sieve-mcp Local macOS scanner for secrets leaked into AI tool chat transcripts, with redacted findings, placeholder-only | 1 ★ | Low risk |
| frisk Screen x402 payment counterparties before paying: address sanity, payTo swap, transport safety and spend polic | 1 ★ | Review before installing |
| verify-proof Verify blockchain-anchored timestamp proofs locally: recompute a file's SHA-256, walk the Merkle path and chec | – | Low risk |
| Identity-AIops Keycloak and Authentik SSO/IAM operations: root-cause analysis for login, permission, client and MFA issues, p | – | Low risk |
| cli Personal identity profiles under a ~name handle, paid lookups that share revenue with the person found, skill- | – | Low risk |
| toolwrit Policy sidecar for any MCP server: deny-by-default tool allowlist with argument rules, call and USD budget cap | – | Low risk |
| hallucc-mcp Claim-level hallucination detection with sources, agent trajectory verification, risk gating for computer-use | – | Low risk |
| Compliance-AIops Turn other AIops tools' audit trails into tamper-evident, hash-chained evidence bundles mapped to HIPAA, PCI-D | – | Low risk |
| basescope Read-only safety checks for Base and EVM: honeypot and rug-pull detection, risky approvals, verified source, b | – | Low risk |
| mcp-audit-gateway Transparent MCP proxy that keeps a signed, hash-chained audit trail of agent tool calls, with YAML policy enfo | – | Low risk |
| 54ch10-mcp JSON risk briefs for wallet addresses, tokens and URLs: scores, flags and sources from phishing, scam and URL- | – | Low risk |
| lazaretto-mcp Check lockfiles against malicious-package advisories and scan artifacts for credential theft, exfiltration, ob | – | Low risk |
| verity-mcp Fail-closed trust gate for agents: fact-checking, prompt-injection detection, content moderation, PII and secr | – | Low risk |
| eleion-scanner-mcp Register and verify domains, queue security scans (headers, TLS, DNS, ports, CVEs and AI-specific checks) and | – | Low risk |
| aimarket-oracle-gateway Verifiable oracle tools via AIMarket Hub: Platon VRF randomness, Chronos VDF computation and verification, and | – | Low risk |
| blackwall-mcp Risk gate that agents call before irreversible actions, returning a risk score, reversibility class, red flags | – | Low risk |
| state-of-cwv-mcp Core Web Vitals metrics by CMS, CDN and framework, based on Chrome field data and a multi-site crawl. | – | Low risk |
| governed-mcp-gateway HTTP MCP gateway that attaches a principal to tool calls and SSE streams, with allowlists and vault rotation. | – | Low risk |
| trust-ledger-os Trust and risk control plane for AI teams, with phases, routes and a package catalog. | – | Low risk |
| umbra Trust scores and guardrails for AI-generated code: static security rules, Docker-verified build/boot checks an | – | Low risk |
| x402-notary-mcp Notarize AI model outputs with signed Ed25519 attestations, SHA-256 content hashes and Merkle anchoring on Bas | – | Low risk |
| rqwstr-mcp HTTP security testing toolkit (send, intruder, race, chain, out-of-band) with low-level HTTP/1.1 and HTTP/2 co | – | Low risk |
| vorim-mcp-server Agent identity, trust and audit trails: Ed25519 agent registration, permission checks, tamper-evident audit ev | – | Low risk |
| tamperlens-mcp Document forensics via the Tamperlens API: detect post-creation edits, failed redactions and embedded prompt i | – | Review before installing |
| vulnfeed-mcp Scans dependency lockfiles for vulnerabilities, prioritizes them by EPSS exploit probability and recommends fi | – | Low risk |
| rails-mcp Self-hosted default-deny action registry, append-only spend-intent ledger and human sign-off audit trail for g | – | Low risk |
| mandare Accountability for AI agent fleets: verify a signed, hash-chained ledger, check budgets, kill an agent, and is | – | Low risk |
| mcp-security-guard Audit the MCP servers you use against the OWASP MCP Top 10: tool poisoning, rug pulls, shadowing, secrets and | – | Low risk |
| feldspar-scan Deterministic security scan of public git repositories: vulnerable dependencies via OSV, hard-coded secrets an | – | Low risk |
| etch-mcp Signed audit chain for AI agent decisions: events are signed, Merkle-chained per project, anchored to public t | – | Low risk |
| safenode-mcp-gateway Fail-closed policy proxy for MCP tool calls that denies, warns on or holds each call for human approval before | – | Low risk |
| SaveSaveSaveSave Read-only checks before an agent acts: prompt-injection and phishing scan of untrusted text (local), npm packa | – | Low risk |
| aws-audit-scanner Read-only AWS audit scanner: public S3 buckets, root and user MFA gaps, unused access keys, world-open securit | – | Low risk |
| mcp Analyze AWS IAM policies and CloudFormation templates with Shieldly to flag privilege-escalation paths, wildca | – | Low risk |
| checker-mcp Local-first domain security and privacy checker: live SPF, DMARC, DKIM, DNSSEC, TLS, CAA and security header c | – | Low risk |
| mcp-server-mcpindex Find MCP servers by describing a task and get advisory trust screens before connecting, using the mcpindex dir | – | Low risk |
| screenverity-mcp U.S. exclusion, debarment and license screening (OIG LEIE, SAM.gov, state boards) with an Ed25519-signed recei | – | Low risk |
| trustscoreagent Check the reputation of AI microservices and public APIs before calling them and submit ratings afterward, via | – | Low risk |
| seal Exactly-once payments for agents: prevents double settlement across processes and retries, confirms charges wi | – | Low risk |
| skillguard Static scanner that checks Claude Code skills, plugins and MCP servers for exfiltration, install hooks and pro | – | Low risk |
| ssid-mcp MAC address (OUI) vendor lookup with randomized-address detection, plus router default login IPs and admin cre | – | Low risk |
| smallprint-action Query the Small Print record: versioned, diffed tool descriptions and schemas of MCP servers, skills and plugi | – | Low risk |
| blastradius-mcp Zero-trust security proxy, pre-execution blast radius simulation, DLP secret redaction, and cryptographic audi | – | Low risk |
| verax Sits between an agent and its tools: every call passes a policy gate and leaves a signed decision record befor | – | Low risk |