An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Prompt Injection Detection Engine to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Stop malicious hijacking attempts before they reach your agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 3 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Prompt Injection Detection Engine.

  1. 01

    Analyze injection risk

    This capability provides a qualitative risk assessment of a specific input. It evaluates the severity of detected patterns to help you decide if a request should be blocked.

  2. 02

    Scan text content

    This capability scans a single string of text for prompt injection signatures. It returns a match count and a flag indicating if the content is blocked.

  3. 03

    Get attack definitions

    This capability lets you audit the current signature database. It retrieves the set of known malicious signatures and their categories.

Real work

What teams actually run

01

User Input Filtering

Scan text from a chat interface before it reaches your primary AI model.

02

Agent Security Auditing

Use the attack definitions to verify your system's defense against known hijacking methods.

03

Risk Monitoring

Analyze the risk level of suspicious inputs to categorize threat severity.

04

Instruction Protection

Prevent users from using delimiter misuse to break out of system prompts.

One connector, every AI

Prompt Injection Detection Engine works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Prompt Injection Detection Engine to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

839ms average. Fast in production.

Prompt Injection Detection Engine is checked daily against the live service.

Daily averagePeak 993ms
Oct 5Today
Fastest day
664ms
Slowest day
993ms
14-day trend
Slowing+5%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Prompt Injection Detection Engine, so you can see the experience inside your AI.

It does not authenticate your account with Prompt Injection Detection Engine. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Prompt Injection Detection Engine Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_K7iGRqRRajazSjul2afMfg824IxPaf1VLOxZdHFQ/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Prompt Injection Detection Engine capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "prompt-injection-detection-engine-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_K7iGRqRRajazSjul2afMfg824IxPaf1VLOxZdHFQ/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Prompt Injection Detection Engine in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Prompt Injection Detection Engine owners hand off.

This MCP is built for developers and security engineers building agentic workflows that interact with untrusted user input.

  • 01

    AI Engineers

    They use this to add a security layer to agentic loops.

  • 02

    Security Researchers

    They use the attack definitions to audit and test model robustness.

  • 03

    Product Developers

    They integrate these checks to prevent user-driven instruction overrides.

FAQ

Questions Prompt Injection Detection Engine owners ask.

  • 01

    How does this MCP detect attacks?

    It uses static pattern matching to identify specific signatures like hijacking, role-play overrides, and delimiter misuse.

  • 02

    Can I see what signatures are being used?

    Yes, you can use the get_attack_definitions capability to retrieve the current set of known malicious signatures and categories.

  • 03

    What is the difference between scanning and risk analysis?

    Scanning provides a match count and a block flag, while risk analysis provides a qualitative assessment of the threat severity.

  • 04

    Which AI clients can use this MCP?

    It works with any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 05

    Is the detection deterministic?

    Yes, the engine uses deterministic pattern matching to identify injection attempts.

  • 06

    How does the detection work?

    The engine uses deterministic regex patterns and exact string matching to identify known malicious signatures. It does not rely on LLM heuristics, ensuring fast and predictable results.

  • 07

    What is the difference between scanning and risk assessment?

    The scan_text_content capability provides a binary block flag and match count, while analyze_injection_risk provides a qualitative rating like low, medium, or high.

  • 08

    Can I see the patterns being used?

    Yes, you can use the get_attack_definitions capability to retrieve the current set of known malicious signatures and their categories.

Explore

More in Security

Suggestions

Connect Prompt Injection Detection Engine to Claude, Cursor, ChatGPT & more