安全 MCP 服务器
安全 分类 — 366 个 MCP 服务器,按 GitHub star 数排序。
agentic-wallet-guardian-v3
Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.
dawshund_mcp
Enumerate AWS IAM data, analyze effective permissions and visualize access relationships across users, roles and resources, based on…
scamverify-mcp
Scam and threat checks for phone numbers, URLs, texts, emails, documents and QR codes using FTC/FCC complaints, URLhaus and ThreatFox,…
pod
Least-privilege compiler for agents: record real tool calls, compile a minimal policy, enforce it at an MCP gateway and keep a…
agentscore-mcp-server
Security trust layer that monitors MCP packages on npm for install scripts, command injection, hardcoded secrets, capability drift and…
Algenta MCP Server
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
sphior-code
Deterministic security findings + fix guidance for your AI agent. Runs locally, no account needed.
mcp-regulated-ai-compliance
Regulated-industry AI compliance: EU AI Act, APRA, NIST AI RMF, ISO 42001, AU AI Safety.
vaulted-mcp-server
Share end-to-end encrypted, self-destructing secrets from an agent, reading them from env vars or files so they stay out of LLM context.
wei9072/aegis
Admission control for agent file edits: checks syntax, structural-cost regressions and workspace boundaries, returning BLOCK, WARN or PASS…
HVTracker MCP
Pre-connect trust checks for AI agents and MCP servers using HVTracker's public trust registry.
captcha-mcp
Charge AI agents per-call without accounts. PoW solve = free tier, Lightning = paid tier.
arc-gate-mcp
Runtime governance for MCP tool calls that blocks prompt injection and capability abuse before tool results reach the agent.
Compliance AIops
Compliance evidence from AIops audit trails: HIPAA/PCI/SOC2/GDPR, OSCAL export, 19 tools.
CanaryGuard 402
Deterministic prompt-injection detection & sanitization for AI agents via x402 on Base.
TrustedMCP
A-D grades for MCP servers: look one up, check your MCP config, find graded alternatives.
AIMarket Oracle Gateway
Stdio MCP: 17 verifiable AIMarket oracles, 35 pay-per-call tools for AI agents.
nobulex
Proof-of-behavior enforcement for AI agents: define permit/forbid/require rules, enforce them at runtime and keep hash-chained,…
verify-atom
Signed proof of web observations for AI agents: Ed25519 proof packets for any URL.
AgentAegis
Pay-per-call cybersecurity for AI agents: vuln scans, threat intel, compliance, code security.
Seal
Stops agents double-charging across processes: exactly one execution, confirmed by the provider.
blackwall-mcp
API-key pre-action risk gate: any irreversible agent action (money, SQL, delete, email).
basescope
Read-only safety checks for Base and EVM: honeypot and rug-pull detection, risky approvals, verified source, balances, ENS and Basenames,…
cleimesh
Signed, delegable permissions for AI agents that a WebAssembly sandbox enforces on every tool call, with hash-chained receipts that can be…
AppLedger
Plain-English security checks for AI-built apps (Trivy + Opengrep), with fix requests for agents
State of Web Vitals
Core Web Vitals metrics by CMS, CDN, and framework — free remote MCP, no auth.
governed-mcp-gateway
HTTP MCP gateway that attaches a principal to tool calls and SSE streams, with allowlists and vault rotation.
trust-ledger-os
Trust and risk control plane for AI teams, with phases, routes and a package catalog.
OpsecForge
Local MCP tools that keep secrets out of agent context: redact files, scan commits, verify webhooks.
mcp-audit-gateway
Transparent MCP proxy that keeps a signed, hash-chained audit trail of agent tool calls, with YAML policy enforcement and OpenTelemetry…
Eleion Scanner
Register/verify your domains, queue security scans, and read findings (CVE, severity).
toolwrit
Policy sidecar for any MCP server: deny-by-default tool allowlist with argument rules, call and USD budget caps, and a hash-chained audit…
nemesis_shield_sdks
Positive-security for apps, APIs, LLMs and edge, plus fraud scoring and identity/AML screening.
skillguard
Static scanner that checks Claude Code skills, plugins and MCP servers for exfiltration, install hooks and prompt injection before you…
Living Stack Community
Save your coding agent's exact next step and load it after a restart. Free MCP server, no account.
x402 Notary MCP
Cryptographic receipts for AI outputs on Base or Solana via x402.
HallucC — Hallucination & Safety Guardian
Fact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.
verify-proof
Verify timestamp proofs offline, anchor hashes through ProofLedger, keep agent run receipts.
tamperlens-mcp
Was this document edited, did its redactions hold, is it safe for a model to read — Tamperlens API.
redproof-mcp
Security checks for apps built with AI coding tools (Lovable, Bolt, Cursor, Claude Code): scan a public GitHub repo for open Supabase…
VulnFeed
Dependency vulnerability scanner with EPSS scoring. 9 MCP tools. Free tier + x402.
rails-mcp
Default-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).
rqwstr-mcp
AI-native HTTP security testing MCP server — 17 tools with raw HTTP/1.1 + HTTP/2 control
Perspective API Alternative (Toxicity Detection)
Toxicity scores (0-1) for text before an agent posts it. Perspective API compatible. No LLM.
vorim-mcp-server
AI agent identity, permissions, trust scores, and tamper-evident audit trails via Vorim AI
qURL
Share local apps with approved reviewers. Identity before connection; zero public inbound app ports.
mcp-server-mcpindex
Find MCP servers by describing a task and get advisory trust screens before connecting, using the mcpindex directory.
verity-mcp
Fail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402.
attest — verification for AI agent artifacts
Verify an AI agent artifact: schema, emptiness, provenance and mandate authority, Ed25519-signed.
checker-mcp
Domain security & privacy checker as an MCP server. 17 live checks, 0-100 score, local-first.
MCP Security Guard
Audit MCP servers for tool poisoning, rug pulls and supply-chain risk (OWASP MCP Top 10).
SecureInput
Type API keys into a native inline input instead of the chat; delivered to a local command or .env.
Web3 Systemic Agent
Web3 security & DAO auditor: free bytecode/honeypot/Snapshot tools + x402 Gemini LLM deep audit.
Latchpoint
Offline, read-only auditing of MCP client configuration files with redacted findings
54ch10-mcp
JSON risk briefs for wallet addresses, tokens and URLs: scores, flags and sources from phishing, scam and URL-reputation heuristics,…
etch-mcp
Etch is a signed audit chain for AI agent decisions, offline-verifiable against pinned public keys.
guardrail-mcp
Enterprise security and code-safety guardrail for AI agents featuring AST taint analysis, SARIF/SBOM generation, and policy gates.
shieldly-io/mcp
AI-Powered AWS security analysis: scan IAM policies and CloudFormation for risks and escalation.
Deus Witness
MCP proxy: holds risky tool calls for passkey approval; signed receipts you can check offline.
SafeNode MCP Gateway
Policy proxy for MCP tool calls. A denied call never reaches the downstream server.