MCP server Security terbaik untuk Claude Code

Securely execute LLM-generated code in isolated containers or local Linux and Windows sandboxes across multiple programming languages.

claude mcp add llm-sandbox -- uvx llm-sandbox

Enforces policy-as-code governance for AI agents through deterministic scheduling and verifiable audit receipts.

claude mcp add bernstein -- uvx bernstein

Reverse engineer binaries, applications, and runtime behavior through an AI agent or terminal interface.

claude mcp add rea -- npx -y rea-agents

Provides LLM agents with controlled, audited SSH access to remote Linux and Windows hosts using policy-based authorization and human-in-the-loop approvals.

claude mcp add ssh-mcp -- npx -y ssh-mcp

Provides encrypted, fully offline, and durable agentic memory for AI agents to store and recall facts, preferences, and decisions locally.

claude mcp add compartment -- uvx compartment

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

Provides an AI-powered OSINT toolkit that lets agents perform passive reconnaissance using tools for DNS, WHOIS, IP, and breach lookups.

claude mcp add openosint-2b2261 -- uvx openosint

Provides an AI-powered OSINT toolkit that lets agents perform passive reconnaissance using tools for DNS, WHOIS, IP, and breach lookups.

claude mcp add openosint -- uvx openosint

Lets AI clients run private web searches, read URLs, and get query suggestions through a SearXNG instance.

claude mcp add mcp-searxng -- npx -y mcp-searxng

Enables AI agents to perform security research, vulnerability analysis, and automated code fixing through a specialized security harness.

claude mcp add 0 -- npx -y 0sec-cli

Enables AI assistants to perform professional network analysis, security audits, and threat detection using tshark and packet capture files.

claude mcp add wireshark-mcp -- uvx wireshark-mcp

Provides a chain of custody for AI agents by issuing signed receipts for tool calls and enforcing access policies via an MCP gateway.

claude mcp add agent-custody -- npx -y @agent-custody/receipts

Validates architectural decision records against your actual code, detects drift, masks sensitive content, and tracks decisions.

claude mcp add mcp-adr-analysis-server -- npx -y mcp-adr-analysis-server

Enables 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}/mcp

Hardens binaries, Electron apps, JS bundles, Python, and WebAssembly artifacts against AI reverse-engineering agents.

claude mcp add bla -- npx -y bla-agents

Analyze customer feedback by stripping PII before processing to find stable themes and provide cited evidence for AI agents.

claude mcp add obsei -- uvx obsei

Puts 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/mcp

Allows AI clients to search a community library of threat hunting hypotheses by keyword, threat actor, or available log sources.

claude mcp add hearth -- npx -y @thorcollective/hearth-mcp