Back to Home
CryptoLabInc icon

envector-mcp-server

by CryptoLabInc

Overview

Provides a Model Context Protocol (MCP) server that enables AI applications to securely access and search homomorphically encrypted vector data stored in enVector, suitable for private networks and secure data environments.

Installation

Run Command
python srcs/server.py --mode "http" --host "localhost" --port "8000" --server-name "envector_mcp_server" --envector-address "YOUR_ENVECTOR_HOST:50050" --envector-key-id "mcp_key" --envector-key-path "YOUR_KEY_PATH" --embedding-mode "femb" --embedding-model "sentence-transformers/all-MiniLM-L6-v2"

Environment Variables

  • MCP_SERVER_MODE
  • MCP_SERVER_HOST
  • MCP_SERVER_PORT
  • MCP_SERVER_ADDRESS
  • MCP_SERVER_NAME
  • ENVECTOR_ADDRESS
  • ENVECTOR_CLOUD_ACCESS_TOKEN
  • ENVECTOR_KEY_ID
  • ENVECTOR_KEY_PATH
  • ENVECTOR_EVAL_MODE
  • ENVECTOR_ENCRYPTED_QUERY
  • EMBEDDING_MODE
  • EMBEDDING_MODEL
  • OPENAI_API_KEY

Security Notes

The `document_preprocess.py` module's `_load_documents_from_path` function takes a `path` parameter from tool arguments and uses `pathlib.Path(path)` and `root.glob(pattern)` to read files. If this `document_path` is controlled by an untrusted client (e.g., via a malicious AI prompt), it presents a significant path traversal vulnerability, potentially allowing unauthorized reading of files outside the intended directory or denial-of-service. There is no clear input sanitization for `document_path`. While configuration is handled via environment variables/CLI (avoiding hardcoded secrets), and the default HTTP bind host is localhost (improving default security), the path traversal risk is critical. The `_to_json_available` method's fallback to `repr(obj)` could potentially expose sensitive object states in logs/errors, but is a lesser concern.

Similar Servers

Stats

Interest Score10
Security Score4
Cost ClassMedium
Avg Tokens500
Stars1
Forks0
Last Update2025-12-19

Tags

Homomorphic EncryptionVector SearchAI ToolsData SecurityRAG