Search

VirusTotal MCP Server是一个让AI结合威胁情报进行深入分析、基于 Model Context Protocol (MCP) 开发的 VirusTotal API 调用工具，为用户提供文件、IP地址、域名和URL的威胁情报查询功能，并将得到的数据喂给AI进行二次分析，提升威胁情报分析能力并给予处置建议。

Data-sensitivity inventory for AI agent tool surfaces — catalog every MCP tool across your fleet, classify by risk and data sensitivity, feed governance workflows.

Runtime governance proxy for MCP servers. Risk scoring, hash-chained audit, per-tenant policy.

OAuth/OIDC authentication adapter for MCP clients

A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine

Lint Dockerfiles for root users, latest tags, secrets in ENV or ARG, missing HEALTHCHECK and more.

Runtime + semantic trust registry for MCP servers - catches tool poisoning and scope creep, $0 infra (local LLM via Ollama)

SimpliSafe MCP server for Claude — developed and maintained by AI (Claude Code)

Build llms.txt from local Markdown or a sitemap.xml and check an existing llms.txt file.

A vendor-neutral collection of Sigma, YARA, and Suricata rules for detecting compromise of LLM applications, MCP servers, ML supply chains, AI infrastructure, AI-powered insider threats, and RAG/vector database attacks.

Input sanitizer for AI agents — anti-prompt-injection shield

AgentLock authorization middleware for MCP (Model Context Protocol) servers.

CYBERDUDEBIVASH Autonomous Zero-Trust AI Cybersecurity Command Center (MCP Server)

Slurp is an HTTP/HTTPS inspection and API testing tool with a Rust proxy, a browser-based workspace, and an MCP server. Capture traffic, edit and replay requests, chain API workflows, and review scan findings from one interface.

Prompt injection detection for LLM applications and MCP servers

MCP Proxy — runtime interception for AI agent tool calls using ATR rules

Read-only PostgreSQL for AI agents: every statement is checked before it runs. No account needed.

Zero-Trust Data Sanitization (ZTDS RFC v1.0) reference MCP server for Claude Desktop, Cursor, and Windsurf. In-memory PII de-identification and deterministic surrogate tokenization.

Deterministic MCP proxy that blocks money-moving and data-egress tool calls in any agent session that has received untrusted content. No model in the decision path.

Enforcing proxy for MCP tool calls: every tools/call is checked against an FDIA policy before it reaches the server, with a hash-chained audit log.