Which AI agents does Omnidrive Mcp work with?
Omnidrive Mcp works with any LLM client that supports the MCP standard, including Claude Desktop, Cursor, ChatGPT, and Gemini.
@sp-22
Basic information
The secure, local-first gateway that bridges your personal files to any AI Agent.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"omnidrive": {
"command": "<UI Friendly so once installed you can copy config as per your installation>",
"args": []
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Omnidrive Mcp is a secure, local-first desktop application that bridges personal files to any AI Agent via the Model Context Protocol (MCP). It allows you to selectively share local folders with AI assistants like Claude Desktop, Cursor, ChatGPT, and Gemini, giving them the ability to read and interact with your documents, spreadsheets, and code while keeping you in full control.
Download the latest installer from the GitHub Releases page, open the application, and add folders you want to share with your AI agent. No terminal commands or environment variables are needed; the clean UI lets you set permissions (read-only or read/write) and see all activity in a dedicated Live Activity Log window.
.mcpignore files to exclude irrelevant directoriesOmnidrive Mcp works with any LLM client that supports the MCP standard, including Claude Desktop, Cursor, ChatGPT, and Gemini.
No. Files are never uploaded to OmniDrive servers; all data transfers happen over a local process pipe or a secure local SSE bridge locked to 127.0.0.1.
It uses canonical path validation against a whitelist of approved absolute paths, sandbox isolation to prevent path traversal, and paired SSE connections that require a secure handshake
🚀 The fast, Pythonic way to build MCP servers and clients.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
Comments