MCP servers remotos
43.913 servidores que conectas por URL mediante streamable HTTP. Nada que instalar ni mantener en ejecución en tu máquina.
43.913 servidores que conectas por URL mediante streamable HTTP. Nada que instalar ni mantener en ejecución en tu máquina.
Pega su repositorio de GitHub y lo listaremos tras una revisión rápida.
Enviar servidorUn MCP server remoto se ejecuta en la infraestructura de otra persona y tu cliente se conecta a él por URL mediante streamable HTTP (los servidores más antiguos usan SSE). El inicio de sesión suele hacerse con OAuth en el navegador en lugar de una clave API en un archivo de configuración.
Los servidores locales se ejecutan como un proceso en tu máquina y pueden acceder a tus archivos y red privada. Los servidores remotos no necesitan un runtime y se actualizan solos, pero tus datos van al proveedor. Elige remoto para productos SaaS y local para archivos, bases de datos en tu red y todo lo que funcione sin conexión.
En Claude Code ejecuta claude mcp add --transport http <name> <url>. En Cursor y Gemini CLI agrega la URL en mcpServers; en VS Code agrégala en servers con "type": "http". Cada página de servidor tiene la configuración exacta.
Scans and investigates AI supply chains by mapping agents, MCP servers, packages, and their potential reach to identify vulnerabilities.
$claude mcp add agent-bom -- uvx agent-bomEnables AI clients to securely access metadata management capabilities including search, lineage, data quality, and governance through OAuth 2.0.
$claude mcp add --transport http openmetadata-mcp https://{openmetadata_host}/mcpPuts authorization in front of AI agent HTTP actions, forwarding only requests approved by the Decionis authority and holding or blocking the rest.
$claude mcp add agent-safe-pipeline -- npx -y @decionis/mcpScans domains for DNS, email security, and deliverability issues, checks SPF/DKIM/DMARC/DNSSEC, and generates fix records.
$claude mcp add intodns-mcp-server -- npx -y intodns-mcpEvaluates AI agent proposals against thirteen constitutional floors to provide governed verdicts and auditable receipts before execution.
$claude mcp add arifos-mcp -- uvx arifosGives 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-intelligenceChecks and signs every AI agent tool call before it runs, holds risky calls for human approval, and exports tamper-evident records anyone can verify offline.
$claude mcp add --transport http tracekit https://{tracekit_gateway}/mcpGives AI clients persistent memory across sessions, enforces saved rules before actions, and reviews finished work against intent.
$claude mcp add cogmemai-mcp -- npx -y cogmemai-mcpLets an AI agent recall and calibrate policy-compliant tool-call arguments to prevent unauthorized or incorrect tool execution.
$claude mcp add achromat-mcp-server -- npx -y @achromat-ai/mcp-serverLets AI clients securely access and manage FHIR healthcare data stored in Medplum.
$claude mcp add --transport http medplum https://api.medplum.com/mcp/streamRuns 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-mcpPerforms 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-mcpProvides 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-mcpDetect malicious or vulnerable npm packages through registry searches, OSV.dev lookups, and GitHub advisory checks.
$claude mcp add --transport http npmscan-mcp-plugin https://npmscan.com/api/mcpEnables 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-mcpEnforces guardrails for LLM outputs by providing safety and quality verdicts, recommended actions, and transaction simulation.
$claude mcp add overwing-mcp -- npx -y overwing-mcpHelio acts as an MCP proxy that enforces governance policies, spend limits, and approval workflows for AI agents without changing their code.
$claude mcp add helio -- npx -y @gethelio/proxyAllows AI agents to fetch TOTP codes for shared 2FA accounts to complete sign-in processes automatically.
$claude mcp add mcp-server -- npx -y @authn8/mcp-serverGives AI agents their own email inbox to send, receive, reply to, and route messages for human approval.
$claude mcp add --transport http mcp-server https://api.e2a.dev/mcpProvides AI agents with email addresses, encrypted credential storage, and behavioral trust scoring via MCP tools.
$claude mcp add agentlair -- npx -y @agentlair/mcp