RUN IN TERMINAL
claude mcp add copromptguard-security -- uvx promptguard-mcp-server
ADD TO claude_desktop_config.json
{
"mcpServers": {
"copromptguard-security": {
"command": "uvx",
"args": ["promptguard-mcp-server"]
}
}
}
ADD TO .vscode/mcp.json
{
"mcpServers": {
"copromptguard-security": {
"command": "uvx",
"args": ["promptguard-mcp-server"]
}
}
}
ADD TO .cursor/mcp.json
{
"mcpServers": {
"copromptguard-security": {
"command": "uvx",
"args": ["promptguard-mcp-server"]
}
}
}
About This MCP Server
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client. This is a Model Context Protocol (MCP) server that extends AI assistants like Claude with ai & machine learning capabilities via the stdio transport.
Package
promptguard-mcp-server on pypi
HOW TO USE
Select your AI client above to get the install command. This MCP server uses the stdio transport and is available on pypi.
What tools does it provide?
The PromptGuard server extends your AI assistant with ai & machine learning capabilities. Once installed, your AI can use its tools automatically.
