MCP servers remotos
43.210 servers que você conecta por URL via streamable HTTP. Nada para instalar ou manter rodando na sua máquina.
Filtros · 2
Confiança
Linguagem
Categoria
158 resultados
ServidorCapacidadesEstrelas · 30d
43.210 servers que você conecta por URL via streamable HTTP. Nada para instalar ou manter rodando na sua máquina.
Cole o repositório do GitHub e nós o listaremos após uma rápida revisão.
Enviar servidorUm MCP server remoto roda na infraestrutura de outra pessoa e seu cliente se conecta a ele por URL via streamable HTTP (servers mais antigos usam SSE). O login geralmente acontece via OAuth no navegador em vez de uma chave de API em um arquivo de configuração.
Servers locais rodam como um processo na sua máquina e podem acessar seus arquivos e rede privada. Servers remotos não precisam de runtime e se atualizam sozinhos, mas seus dados vão para o provedor. Escolha remoto para produtos SaaS, local para arquivos, bancos de dados na sua rede e qualquer coisa offline.
No Claude Code, execute claude mcp add --transport http <name> <url>. No Cursor e no Gemini CLI, adicione a URL em mcpServers; no VS Code, adicione em servers com "type": "http". Cada página de server tem a configuração exata.
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-bom
Evaluates AI agent proposals against thirteen constitutional floors to provide governed verdicts and auditable receipts before execution.
$claude mcp add arifos-mcp -- uvx arifos
Checks 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}/mcp
Verifies paid AI agent services using signed receipts and real-time measurements to prevent incorrect payments.
$claude mcp add --transport http botsrated https://botsrated.com/mcp
Provides threat intelligence by allowing AI agents to retrieve reports for files, URLs, domains, and IP addresses, and submit new analysis requests.
$claude mcp add virustotal-mcp -- uvx vt-mcp
Provides cryptographic proof of existence for digital artifacts and AI agent checkpoints via notarized receipts anchored to the NEAR blockchain.
$claude mcp add aotrust-skills -- uvx aotrust-protocol
Lets an AI client check emails and domains against known data breaches, view breach analytics, and browse breach metrics.
$claude mcp add --transport http xposedornot-api https://api.xposedornot.com/mcp
Provides AI agents with live threat intelligence including incident clusters, actor profiles, CVE exploit status, and ransomware leak-site victims.
$claude mcp add threat-intelligence-mcp -- npx -y threatcluster-mcp
Scans PDFs, Office documents, and RAG inputs for malware exploits, CVEs, and hidden AI prompt injections.
$claude mcp add malwaretracker-mcp -- uvx malwaretracker-mcp
Acts as a governance proxy between AI agents and MCP servers to enforce allowlists, dry runs, human confirmation, and audit trails.
$claude mcp add mcp-airlock -- uvx mcp-airlock
Lets an AI client list, inspect, and grant or deny pending CTRLRun approval requests.
$claude mcp add ctrlrun -- uvx ctrlrun
Lets an AI client run allowlisted, audited commands and structured file edits on Linux, macOS, and Windows hosts.
$claude mcp add --transport http sentinelx-cloud-core https://mcp.sentinelx.app/mcp/mcp
Enables AI assistants to query the Vulners vulnerability database for CVE information, security bulletins, and software package auditing.
$claude mcp add vulners-mcp -- uvx vulners-mcp
Provides a centralized HTTP gateway for AI agents to perform controlled SSH commands and SFTP file transfers with audit logging and command policies.
$claude mcp add ssh-mcp -- docker run -i --rm ghcr.io/gelse/ssh-mcp:0.3.0
Enables AI agents to verify identities, manage credentials, and perform trust scoring across decentralized networks and commerce platforms.
$claude mcp add --transport http moltrust-mcp-server https://api.moltrust.ch/mcp
Scans Android and iOS applications for security vulnerabilities and generates pentest reports mapped to OWASP MASVS, CWE, and CVSS.
$claude mcp add gomobsec-mcp -- uvx gomobsec-mcp
Provides role-based access control to a Qdrant vector database by converting OIDC tokens into scoped Qdrant JWTs.
$claude mcp add qdrant-mcp-rbac -- docker run -i --rm ghcr.io/fidonis/qdrant-mcp-rbac:0.4.1
Sign media with C2PA Content Credentials, add invisible watermarks, and verify file origins through an AI assistant.
$claude mcp add mcp -- uvx originalpictures-mcp
Verifies AI agent actions through multi-model adversarial consensus and provides signed, cryptographically verifiable decision receipts.
$claude mcp add ethersflow -- npx -y @ethersflow/mcp-server
Detects prompt injection, jailbreaks, and data exfiltration in untrusted text before it reaches an LLM.
$claude mcp add safeprompt -- npx -y @safeprompt.dev/mcp