Markdown Vault MCP
v3.1.0
MCP ServerMCP Registry
io.github.pvliesdonk/markdown-vault-mcp
Markdown vault MCP server with FTS5 + semantic search and frontmatter indexing
stdiostreamable-httppypiociregistry 收录
io.github.Vishisht16/humane-proxy · v0.6.0
AI safety middleware — detects self-harm and criminal intent in LLM prompts.
humane-proxy 是一个MCP Server，收录自 官方 MCP Registry。支持 stdio 传输。本页提供 Cursor、Claude Code 等客户端的安装配置片段。
选择你的平台查看安装方式
{
"mcpServers": {
"humane-proxy": {
"command": "uvx",
"args": [
"humane-proxy"
]
}
}
}OPENAI_API_KEY可选secretOpenAI API key for Stage 3 reasoning (optional)
GROQ_API_KEY可选secretGroq API key for LlamaGuard Stage 3 (optional)
{
"id": "io.github.Vishisht16/humane-proxy",
"type": "mcp-server",
"version": "0.6.0",
"displayName": "humane-proxy",
"description": "AI safety middleware — detects self-harm and criminal intent in LLM prompts.",
"repository": {
"url": "https://github.com/Vishisht16/Humane-Proxy",
"source": "github"
},
"distribution": {
"packages": [
{
"registryType": "pypi",
"identifier": "humane-proxy",
"version": "0.6.0",
"transport": "stdio",
"environmentVariables": [
{
"name": "OPENAI_API_KEY",
"description": "OpenAI API key for Stage 3 reasoning (optional)",
"isSecret": true
},
{
"name": "GROQ_API_KEY",
"description": "Groq API key for LlamaGuard Stage 3 (optional)",
"isSecret": true
}
]
}
],
"remotes": []
},
"dependencies": [],
"installTargets": [
"claude-code",
"claude-desktop",
"cursor",
"vscode"
],
"keywords": [],
"provenance": {
"origin": "official-mcp-registry",
"originalId": "io.github.Vishisht16/humane-proxy",
"originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.Vishisht16%2Fhumane-proxy/versions/latest",
"isOfficial": true,
"status": "active"
}
}