NestDaddy

SafePrompt

dev.safeprompt/mcp · v0.1.1

Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.

Connect Remote server

Terminal
claude mcp add --transport http mcp https://mcp.safeprompt.dev/mcp --header "X-SafePrompt-Api-Key: <X_SAFEPROMPT_API_KEY>"
~/.cursor/mcp.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.safeprompt.dev/mcp",
      "headers": {
        "X-SafePrompt-Api-Key": "<X_SAFEPROMPT_API_KEY>"
      }
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.safeprompt.dev/mcp",
      "headers": {
        "X-SafePrompt-Api-Key": "<X_SAFEPROMPT_API_KEY>"
      }
    }
  }
}
Claude Desktop
Settings > Connectors > Add custom connector
URL: https://mcp.safeprompt.dev/mcp

Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.

Tools 2 found in our last check

  • validate_prompt

    Check a single piece of untrusted text (a user message, a retrieved RAG document, tool output, etc.) for prompt injection, jailbreaks, instruction-override, data-exfiltration, and code injection BEFORE passing it to an LLM. Returns a safe/unsafe verdict with confidence, threat c…

  • validate_prompts

    Validate many pieces of untrusted text in one call (processed in parallel server-side). Use for bulk pre-screening, indexing pipelines, or checking a batch of retrieved documents. Returns one verdict per input, in order.

Headers

NameDescription
X-SafePrompt-Api-Key
Required, secret
SafePrompt API key from https://dashboard.safeprompt.dev

Details

Endpointhttps://mcp.safeprompt.dev/mcp (Streamable HTTP)
Package@safeprompt.dev/[email protected] (NPM, stdio)
First published29 Oct 2026
Last updated29 Oct 2026
Registry namedev.safeprompt/mcp

More ai and media servers See all

Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.