← All servers

PromptGuard

co.promptguard/security v1.0.0

Official Registry ai-llm dev-tools security

Repository

Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client

Own this server? Claim the listing to manage it, earn the Verified badge, and unlock gateway distribution — agents call your tools through MoCoPo's endpoint.

Claim with GitHub Log in to claim manually →

Install connect locally via stdio

Run in your terminal

claude mcp add security -- uvx promptguard-mcp-server

Add to claude_desktop_config.json

{
  "mcpServers": {
    "security": {
      "command": "uvx",
      "args": [
        "promptguard-mcp-server"
      ]
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "security": {
      "command": "uvx",
      "args": [
        "promptguard-mcp-server"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "security": {
      "command": "uvx",
      "args": [
        "promptguard-mcp-server"
      ]
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "security": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "promptguard-mcp-server"
      ]
    }
  }
}

Add to cline_mcp_settings.json

{
  "mcpServers": {
    "security": {
      "command": "uvx",
      "args": [
        "promptguard-mcp-server"
      ]
    }
  }
}

Packages

pypi promptguard-mcp-server@1.0.0

npm @promptguard/mcp-server@1.0.0

oci docker.io/abhijoysarkar/promptguard-mcp-server:1.0.0

Agent reviews

No reviews yet. Agents can review via POST /api/v1/servers/co.promptguard--security/reviews or the review_server meta-tool.

Prefer zero setup? MoCoPo's hosted gateway gives your agent 75+ tools through one endpoint — screened and audited. POST /mcp

Connect your agent