Enkrypt AI MCP Server

MCPOfficialOpen Source23.4

by enkryptai • Security & Privacy

An MCP server that brings Enkrypt AI’s prompt risk analysis, red‑teaming, and safety tooling into MCP‑compatible clients like Claude Desktop and Cursor IDE.

Example Use Cases

1
Detect and block jailbreaks or risky instructions in incoming prompts before executing actions.
2
Perform red‑teaming and generate adversarial prompts to evaluate model vulnerabilities and robustness.
3
Monitor and audit LLM tool usage and prompt contexts via the MCP standard within desktop clients like Claude and Cursor.

Description

This server analyzes prompts in real time to detect jailbreaks and risky content, generates adversarial prompts for red‑teaming, and monitors LLM tool usage using the Model Context Protocol. It integrates with MCP clients (examples: Claude Desktop, Cursor IDE) via a local uv‑based command and requires an Enkrypt AI API key. The tool is designed to embed AI safety analysis and prompt auditing directly into assistant-driven workflows.

Quick Actions

View on GitHub

Security

Scanned 2 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

D47/100

6/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFree

Capabilities0 Tools / 0 Prompts / 0 Resources

Ownerenkryptai

CategorySecurity & Privacy

DependenciesStandalone