SafePrompt

dev.safeprompt/mcpVersion 0.1.1

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

Status

Responds110 msNov 14, 2026, 14:27 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 14:27 UTC
Latency: 110 ms
Remotes responding: 1 of 1
Sign-in: API key
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 22:14 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://mcp.safeprompt.dev/mcpResponds110 msNov 14, 2026, 14:27 UTC

No sign-in

Claude Code

claude mcp add --transport http safeprompt https://mcp.safeprompt.dev/mcp --header 'X-SafePrompt-Api-Key: <YOUR_X_SAFEPROMPT_API_KEY>'

Replace <YOUR_X_SAFEPROMPT_API_KEY> before running.

Claude Desktop and claude.ai

Settings > Connectors > Add custom connector
Name: safeprompt
Remote MCP server URL: https://mcp.safeprompt.dev/mcp
This server expects the header X-SafePrompt-Api-Key.

Cursor

{
  "mcpServers": {
    "safeprompt": {
      "url": "https://mcp.safeprompt.dev/mcp",
      "headers": {
        "X-SafePrompt-Api-Key": "<YOUR_X_SAFEPROMPT_API_KEY>"
      }
    }
  }
}

Replace <YOUR_X_SAFEPROMPT_API_KEY> before running.

VS Code

code --add-mcp '{"name":"safeprompt","type":"http","url":"https://mcp.safeprompt.dev/mcp","headers":{"X-SafePrompt-Api-Key":"<YOUR_X_SAFEPROMPT_API_KEY>"}}'

Replace <YOUR_X_SAFEPROMPT_API_KEY> before running.

Streamable HTTP

npm: @safeprompt.dev/mcp 0.1.1

Package only

npm (npx)

claude mcp add safeprompt -e 'SAFEPROMPT_API_KEY=<YOUR_SAFEPROMPT_API_KEY>' -- npx -y @safeprompt.dev/mcp@0.1.1

Replace <YOUR_SAFEPROMPT_API_KEY> before running.

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

2 tools

Tools of SafePrompt
	Description		Read-only	Idempotent	Open world
`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 category, and reasoning.	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 category, and reasoning.	No	Yes	Yes	No
`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.	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.	No	Yes	Yes	No

Details

Registry status: Active
Published: Oct 29, 2026
Updated: Oct 29, 2026
Website: https://safeprompt.dev/⁠ (opens in a new tab)
Repository: https://github.com/ianreboot/safeprompt⁠ (opens in a new tab)
Categories (suggested): AI modelsSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing