Security & Testing

promptguard.co

Provides security scanning for text and code to detect threats and redact PII.

1 endpoint6 known toolsFirst detected May 18, 2026Last detected September 5, 2026

ENDPOINT 1

https://api.promptguard.co/mcp

No auth detected

MCP server metadata

Name: promptguard
Version: 1.0.0

Capabilities

experimentalloggingprompts.listChangedresources.listChangedtools.listChangedextensions.io.modelcontextprotocol/ui

Server instructions

PromptGuard -- the firewall for AI prompts. Scan text for prompt injection, redact PII, and audit code for unprotected LLM SDK usage.

Known tools 6

promptguard_scan_text

Scan text for security threats including prompt injection, jailbreaks, PII leakage, and toxic content.

Inferred read-only

promptguard_scan_code

Analyze code for LLM SDK usage patterns (OpenAI, Anthropic, Cohere, Google Gemini, Bedrock).

Inferred read-only

promptguard_redact

Redact PII (emails, phone numbers, SSNs, credit cards, API keys) from text.

Inferred read-only

promptguard_status

Show current PromptGuard configuration and status.

Inferred read-only

search

Search PromptGuard documentation for information about security scanning, PII redaction, proxy setup, CLI usage, and integrations.

Inferred read-only

fetch

Fetch a specific PromptGuard documentation page by ID.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.promptguard]
url = "https://api.promptguard.co/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "promptguard": {
      "type": "http",
      "url": "https://api.promptguard.co/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: promptguard
Remote MCP URL: https://api.promptguard.co/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "promptguard": {
      "url": "https://api.promptguard.co/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "promptguard": {
      "type": "http",
      "url": "https://api.promptguard.co/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "promptguard",
  "transport": "streamable-http",
  "url": "https://api.promptguard.co/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.