Melhores MCP servers de Security para Claude Code

3.540 MCP servers de security com configuração pronta para Claude Code. Abra uma linha para copiá-la.

stdiostreamable HTTP~/.claude.json

Servidores

3.540

Com configuração

1
LLM Sandboxvndee/llm-sandbox1,1 mil estrelas
Securely execute LLM-generated code in isolated containers or local Linux and Windows sandboxes across multiple programming languages.
Configuração para Claude Code
terminal
claude mcp add llm-sandbox -- uvx llm-sandbox
2
Bernsteinsipyourdrink-ltd/bernstein1,2 mil estrelas
Enforces policy-as-code governance for AI agents through deterministic scheduling and verifiable audit receipts.
Configuração para Claude Code
terminal
claude mcp add bernstein -- uvx bernstein
3
REAmorluto/rea458,4 mil estrelas
Reverse engineer binaries, applications, and runtime behavior through an AI agent or terminal interface.
Configuração para Claude Code
terminal
claude mcp add rea -- npx -y rea-agents
4
SSH — policy-gated remote accesstufantunc/ssh-mcp880 estrelas
Provides LLM agents with controlled, audited SSH access to remote Linux and Windows hosts using policy-based authorization and human-in-the-loop approvals.
Configuração para Claude Code
terminal
claude mcp add ssh-mcp -- npx -y ssh-mcp
5
Compartmentmaxfreedompollard/compartment569 estrelas
Provides encrypted, fully offline, and durable agentic memory for AI agents to store and recall facts, preferences, and decisions locally.
Configuração para Claude Code
terminal
claude mcp add compartment -- uvx compartment
6
Agent Bomkoda-ai-studio/agent-bom37 estrelas
Scans and investigates AI supply chains by mapping agents, MCP servers, packages, and their potential reach to identify vulnerabilities.
Configuração para Claude Code
terminal
claude mcp add agent-bom -- uvx agent-bom
7
OpenOSINTopenosint/openosint-2b22611,9 mil estrelas
Provides an AI-powered OSINT toolkit that lets agents perform passive reconnaissance using tools for DNS, WHOIS, IP, and breach lookups.
Configuração para Claude Code
terminal
claude mcp add openosint-2b2261 -- uvx openosint
8
OpenOSINTopenosint/openosint1,9 mil estrelas
Provides an AI-powered OSINT toolkit that lets agents perform passive reconnaissance using tools for DNS, WHOIS, IP, and breach lookups.
Configuração para Claude Code
terminal
claude mcp add openosint -- uvx openosint
9
SearXNG Searchihor-sokoliuk/mcp-searxng1,4 mil estrelas
Lets AI clients run private web searches, read URLs, and get query suggestions through a SearXNG instance.
Configuração para Claude Code
terminal
claude mcp add mcp-searxng -- npx -y mcp-searxng
10
00sec-labs/01,3 mil estrelas
Enables AI agents to perform security research, vulnerability analysis, and automated code fixing through a specialized security harness.
Configuração para Claude Code
terminal
claude mcp add 0 -- npx -y 0sec-cli
11
Wiresharkbx33661/wireshark-mcp399 estrelas
Enables AI assistants to perform professional network analysis, security audits, and threat detection using tshark and packet capture files.
Configuração para Claude Code
terminal
claude mcp add wireshark-mcp -- uvx wireshark-mcp
12
Agent Custodysvayatta/agent-custody104 estrelas
Provides a chain of custody for AI agents by issuing signed receipts for tool calls and enforcing access policies via an MCP gateway.
Configuração para Claude Code
terminal
claude mcp add agent-custody -- npx -y @agent-custody/receipts
13
Adr Analysistosin2013/mcp-adr-analysis-server35 estrelas
Validates architectural decision records against your actual code, detects drift, masks sensitive content, and tracks decisions.
Configuração para Claude Code
terminal
claude mcp add mcp-adr-analysis-server -- npx -y mcp-adr-analysis-server
14
OpenMetadataopen-metadata/openmetadata-mcp15,8 mil estrelas
Enables AI clients to securely access metadata management capabilities including search, lineage, data quality, and governance through OAuth 2.0.
Configuração para Claude Code
terminal
claude mcp add --transport http openmetadata-mcp https://{openmetadata_host}/mcp
15
Blaqybaihe/bla5,7 mil estrelas
Hardens binaries, Electron apps, JS bundles, Python, and WebAssembly artifacts against AI reverse-engineering agents.
Configuração para Claude Code
terminal
claude mcp add bla -- npx -y bla-agents
16
Obseiobsei/obsei1,5 mil estrelas
Analyze customer feedback by stripping PII before processing to find stable themes and provide cited evidence for AI agents.
Configuração para Claude Code
terminal
claude mcp add obsei -- uvx obsei
17
MCP MCPdecionis/agent-safe-pipeline671 estrelas
Puts authorization in front of AI agent HTTP actions, forwarding only requests approved by the Decionis authority and holding or blocking the rest.
Configuração para Claude Code
terminal
claude mcp add agent-safe-pipeline -- npx -y @decionis/mcp
18
HEARTHthorcollective/hearth362 estrelas
Allows AI clients to search a community library of threat hunting hypotheses by keyword, threat actor, or available log sources.
Configuração para Claude Code
terminal
claude mcp add hearth -- npx -y @thorcollective/hearth-mcp

Todos os MCP servers de Security →Configurar MCP no Claude Code →

Adicionar um MCP server ao Claude Code

1Copy the claude mcp add command from the server page.
2Run it in your terminal. Add --scope project to share the server with your team through .mcp.json, or --scope user to use it in every project.
3Pass secrets with --env KEY=value; remote servers take --transport http and the URL.
4Start claude and run /mcp to see the server and its status.

Servers do Claude Code por categoria

Security para outros clientes

Cursor VS Code Claude Desktop Codex Gemini CLI Windsurf Devin Antigravity ChatGPT Zed Cline Continue Goose JetBrains AI Assistant

Verifique antes de instalar

Um servidor local roda com suas permissões. Prefira servidores do próprio editor e dê a cada um o token mais restrito de que precisem.