Secure execution for AI agents, on any machine. Connect any MCP client to the development environment on any machine you can run a command on (even your own laptop) - no open ports, no tunnels, and yo
Secure execution for AI agents, on any machine.
Connect Claude, ChatGPT, Cursor, VS Code or Claude Code to a real project on a server, a VM, a build box, a Raspberry Pi, or the laptop in front of you.
No port to open. No source code to upload. No tunnel to wire up.
That one command signs you in, registers the machine, registers the directory, and prints an MCP URL. Point any client at it and leave connect running.
Hosted: exeora.dev · Docs: exeora.dev/docs · npm: @exeora/cli
Demo. Drop a terminal recording at docs/demo.gif when you have one (see docs/demo.gif.placeholder). Until then, the live product is at exeora.dev.
AI agents are only as useful as the environment they can touch. Today you usually pick one of two bad options:
1. Expose the machine - open a port, run a tunnel, hope the URL stays private. 2. Upload the code - push the repo into a cloud sandbox that is never quite your machine.
Exeora is the third path. The CLI dials out to a gateway and holds a WebSocket open. Nothing ever dials in. Your files stay on the machine they already live on. The agent gets ten tools inside one project directory - not a shell on the whole box, and not a copy in someone else's cloud.
1. You run the CLI in the project directory. It opens an outbound connection to Exeora. No inbound port, no VPN, no ngrok config. 2. You authorize a client once. OAuth 2.1 with PKCE. Each project can be its own URL and its own token, so blast radius is a fact about the path, not a promise the model is asked to keep. 3. The agent works where the code already is - read, search, edit, run commands
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/leynier--exeora.html)
The bridge for remote MCP — seamless OAuth, resilient auth recovery, production-grade reliability
anshupriyan/cli-bridgeMCP server for Claude Desktop and other Model Context Protocol clients — sandboxed filesystem access (read/write/edit/search) plus Dev Mode-gated shell command execution, scoped to a single workspace
illodev/workfileRepository-native Work, Docs, History and durable Memory for humans and AI agents — Markdown as the source of truth, with a local UI, CLI and MCP server
Smitner-Studio/facetRender agent-written Markdown as a live local page, and send the human's click back to the agent as typed data. Human-in-the-loop approval gates for coding agents.
HarjjotSinghh/locumDelegate Grok Bot coding work to your own local Claude Code / Codex CLIs via a custom MCP connector
herry2059/project-os-for-codexOpen-source control plane for Codex projects: Git-backed context, visible agent progress, scoped MCP access, resumable work, and safe handoffs.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.