dev.safeprompt/mcp

up checked 2026-11-11T08:37:44.263Z

Unclaimed · Unverified

Publisher-provided title

SafePrompt

Publisher-provided description

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

Summary by lookupd

Screens untrusted text, including single items or batches, for prompt injection, jailbreaks, and code injection before it reaches an LLM.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http mcp https://mcp.safeprompt.dev/mcp

Claude Code, npm package (stdio)

claude mcp add mcp -- npx -y @safeprompt.dev/mcp

Codex, remote (streamable-http)

codex mcp add mcp --url https://mcp.safeprompt.dev/mcp

Codex, npm package (stdio)

codex mcp add mcp -- npx -y @safeprompt.dev/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.safeprompt.dev/mcp"
    }
  }
}

Cursor, npm package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@safeprompt.dev/mcp"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

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, dat
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 r

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/dev.safeprompt/mcp.svg)](https://lookupd.com/servers/dev.safeprompt/mcp)