mirror-vectax-mcp-server

mirrorsecai/mirror-vectax-mcp-server

3.3

If you are the rightful owner of mirror-vectax-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The Secure Embedding MCP Server is a Model Context Protocol implementation designed for secure text embeddings with privacy-preserving features using the Mirror SDK.

The Secure Embedding MCP Server provides a robust interface for processing text data with various security levels while generating embeddings for semantic search and analysis. It leverages the Mirror SDK to provide advanced security features including format-preserving encryption (FPE) for sensitive entities, vector encryption for secure embeddings, role-based access control (RBAC) for fine-grained security policies, and entity detection for PII and sensitive information. The server is designed to handle multiple text operations through a unified interface, offering configurable security levels and a natural language interface for ease of use. It supports batch processing for efficient handling of multiple texts and enables semantic search across documents using embeddings.

Features

  • Unified Text Processing: Single entry point for various text operations with appropriate security measures.
  • Multiple Operation Modes: Supports 'embed', 'secure', 'analyze', 'mask', and 'auto' modes for text processing.
  • Configurable Security Levels: Offers 'none', 'low', 'medium', 'high', and 'auto' security levels based on content.
  • Natural Language Interface: Allows processing requests in natural language.
  • Batch Processing: Efficiently handles multiple texts for processing.

Usages

usage with Claude Desktop

{
  "mcpServers": {
    "secure-embedding": {
      "command": "uv",
      "args": [
        "--directory",
        "/ABSOLUTE/PATH/TO/YOUR/PROJECT/mirror-vectax-mcp-server",
        "run",
        "mirror_vectax_server.py"
      ]
    }
  }
}

usage with VS Code

{
  "mcp": {
    "servers": {
      "secure-embedding": {
        "command": "uv",
        "args": [
          "--directory",
          "/ABSOLUTE/PATH/TO/YOUR/PROJECT/mirror-vectax-mcp-server",
          "run",
          "mirror_vectax_server.py"
        ]
      }
    }
  }
}

Tools

  1. process

    Handles text processing with various security measures.

  2. batch-process

    Processes multiple texts efficiently.

  3. generate-user-key

    Generates user keys for role-based access control.

  4. search

    Performs semantic search across documents using embeddings.