43,033 件のサーバー は streamable HTTP 経由で URL により接続します。インストールや常駐の必要はありません。
リモート MCP server は他者のインフラ上で動作し、クライアントは streamable HTTP（古いサーバーは SSE）経由で URL により接続します。通常は設定ファイルの API キーではなく、ブラウザでの OAuth によるサインインを行います。
ローカルサーバーはお使いのマシン上でプロセスとして動作し、ファイルやプライベートネットワークにアクセスできます。リモートサーバーはランタイム不要で自動更新されますが、データはプロバイダーに送信されます。SaaS 製品にはリモート、ファイルやネットワーク上のデータベース、オフラインでの利用にはローカルを選んでください。
Claude Code では claude mcp add --transport http <name> <url> を実行します。Cursor と Gemini CLI では mcpServers に URL を追加し、VS Code では servers に "type": "http" とともに追加します。各サーバーのページに正確な設定があります。
Gives AI agents evidence-backed crypto data on prices, wallets, DeFi, token security, DEX flows, and NFTs through one hosted connection.
$claude mcp add hive-sdk -- npx -y hive-intelligence
Runs 30+ domain security checks from an AI client, covering phishing links, exposed admin pages, DNS, SSL, email auth and infrastructure history.
$claude mcp add dechonet-mcp -- npx -y dechonet-mcp
Performs real-time token risk assessments by simulating trades on blockchain forks to detect honeypots and malicious contract functions.
$claude mcp add chaink9-mcp -- npx -y chaink9-mcp
Provides AI agents with a tamper-evident, publicly logged record of actions and events with verifiable offline proofs.
$claude mcp add fabric-verify-mcp -- npx -y @augmentev/fabric-verify-mcp
Enables AI clients to perform CVE, KEV, EPSS, and SBOM lookups with internet-exposure footprints derived from Shodan data.
$claude mcp add echelongraph-mcp -- npx -y echelongraph-mcp
Provides an independent second opinion on AI-generated drafts to catch errors, contradictions, leaked secrets, and prompt injections.
$claude mcp add crosscheck -- npx -y crosscheckapi
Checks Vercel and Supabase applications for security gaps like missing RLS policies, exposed service keys, and unverified Stripe webhooks.
$claude mcp add --transport http viberaven-guides https://viberaven.dev/mcp
Provides security auditing tools for coding agents to discover vulnerabilities, inspect source code, and verify dependency fixes.
$claude mcp add --transport http offense https://offense.sh/mcp
Enables AI agents to detect VPNs, proxies, Tor nodes, hosting providers, and CDNs for any given IP address.
$claude mcp add mcp -- npx -y vpndetection-mcp
Provides security tools for AI agents including command injection gates, SQL validators, Python sandboxing, and PII redaction.
$claude mcp add --transport http diogenes-agent-guardrails-mcp https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails
Checks project lockfiles against security advisories to identify vulnerable packages, runtime flaws, and platform breaches.
$claude mcp add keep-me-secure-mcp -- docker run -i --rm ghcr.io/robertkeus/keep-me-secure-mcp:v1.7.0
Checks TRON USDT (TRC20) addresses for Tether blacklists, sanctions matches, and generates comprehensive AML reports.
$claude mcp add tron-usdt-mcp -- npx -y tron-usdt-mcp
Enables AI agents to perform on-chain address screening, AML compliance checks, and payment intent verification across EVM, Tron, and Solana.
$claude mcp add oceanalt-aml-mcp -- npx -y oceanalt-aml-mcpEnables AI clients to audit smart contracts, analyze Solana token risks, track whale flows, and verify HTTP 402 payment challenges.
$claude mcp add --transport http diogenes-web3-security-mcp https://diogenes-micro-gateway.corinth.workers.dev/mcp/web3-security
Performs AI-powered security analysis on Solidity smart contracts to identify potential vulnerabilities and business-logic flaws.
$claude mcp add --transport http bug-bounty-intelligence-mcp https://wazir-x402.duckdns.org/api/bug-intel
Verifies x402 endpoints to ensure price accuracy, wallet legitimacy, and uptime before an AI agent executes a payment.
$claude mcp add lumiere-paycheck -- npx -y lumiere-paycheck-mcp
Audits AI agent security, MCP schemas, delegation graphs, and behavioral stability with real-time circuit breakers and compliance reporting.
$claude mcp add systemores-plugin -- npx -y @systemores/systemores-pluginScans npm packages, lockfiles, and MCP servers for malicious behavior and known vulnerabilities.
$claude mcp add lazaretto-mcp -- npx -y lazaretto-mcp
Helps security researchers strengthen bug bounty reports by scanning for secrets, verifying evidence, and simulating triager reviews.
$claude mcp add --transport http bounty-operator https://bountyoperator.com/api/mcp
Performs quantitative fixed-income valuation, OFAC sanctions screening, and SEC XBRL forensic accounting analysis.
$claude mcp add --transport http sec-forensics-whistleblower https://ariadnenexus.com/mcp/sec-forensics-whistleblower