SafePrompt MCP

An official MCP server by Reboot, Inc. that allows AI agents to validate untrusted text for prompt injection, jailbreaks, and code injection before processing. It exposes tools to check single or multiple prompts using the SafePrompt API, requiring an API key for authentication.

Visit Reboot, Inc.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Reboot, Inc.

You need:Send your API key in either header: X-SafePrompt-Api-Key: <your key> Authorization: Bearer <your key>Both need a SafePrompt API key from the dashboardVariable Required Purpose SAFEPROMPT_API_KEY Yes Your SafePrompt API key

MCP endpoint (Streamable HTTP)

https://mcp.safeprompt.dev/mcp

Vendor documentation

What you can do with it

Detect prompt injection in user inputs
Identify jailbreak attempts in text
Scan for code injection vulnerabilities
Validate multiple prompts in batch

Source and maintenance

Vendor evidenceRegistry 0.1.1

mcp-registry: dev.safeprompt/mcp@0.1.1 Source repository Project website

Maintenance checked: Nov 1, 2026, 1:00 PM UTC

Protocol and capabilities

Server: safeprompt 0.1.0
MCP protocol: 2025-06-18
Tools: 2 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Validate any untrusted text for prompt injection before passing it to an LLM. Requires a SafePrompt API key sent via Authorization: Bearer <key> or X-SafePrompt-Api-Key.

Tools

2 advertised

validate_prompt — Validate a prompt for injection attacks

Advertised by the server during the last successful anonymous check.

Advertised read-only

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.

validate_prompt input schema

{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "maxLength": 50000,
      "minLength": 1,
      "description": "The untrusted text to validate."
    },
    "sensitivity": {
      "enum": [
        "strict",
        "no_judgement",
        "balanced",
        "lenient"
      ],
      "type": "string",
      "description": "Optional. Omit to use the account default. 'no_judgement' blocks only clear attacks, for apps whose users tell the AI exactly what to write. 'balanced' is an older name for it. 'strict' and 'lenient' are accepted for existing callers."
    }
  },
  "additionalProperties": false
}

validate_prompt annotations

{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

validate_prompts — Batch-validate multiple prompts

Advertised by the server during the last successful anonymous check.

Advertised read-only

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_prompts input schema

{
  "type": "object",
  "required": [
    "prompts"
  ],
  "properties": {
    "prompts": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 50000,
        "minLength": 1
      },
      "maxItems": 100,
      "minItems": 1,
      "description": "Array of untrusted texts to validate (max 100)."
    },
    "sensitivity": {
      "enum": [
        "strict",
        "no_judgement",
        "balanced",
        "lenient"
      ],
      "type": "string",
      "description": "Optional. Omit to use the account default. 'no_judgement' blocks only clear attacks, for apps whose users tell the AI exactly what to write. 'balanced' is an older name for it. 'strict' and 'lenient' are accepted for existing callers."
    }
  },
  "additionalProperties": false
}

validate_prompts annotations

{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 293 ms
95th percentile latency: 293 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 1, 2026, 1:22 PM UTC · probe · passed · 293 ms · metadata changed · 2 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

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

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

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

Cursor

Merge this server into .cursor/mcp.json in your project, then enable safeprompt-mcp in your MCP settings.

Cursor configuration

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

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "safeprompt-mcp": {
      "type": "streamableHttp",
      "url": "https://mcp.safeprompt.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start safeprompt-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "safeprompt-mcp": {
      "type": "http",
      "url": "https://mcp.safeprompt.dev/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

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

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

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

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "safeprompt-mcp": {
      "serverUrl": "https://mcp.safeprompt.dev/mcp"
    }
  }
}

Let your agent find its tools

Find servers like SafePrompt MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 4,318

Do you run SafePrompt MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing