
Leash integrations for AI clients. Configurable protections, activity history and supported undo
Leash integrations for AI clients. Configurable protections, activity history and supported undo through your connected accounts.
·
A little peace of mind for your AI. Free.
Leash connects your AI to your accounts through configurable protections. Review activity, control each AI's access, and undo supported reversible actions when undo is enabled. Only activity routed through Leash is covered.
Install Leash from your AI's plugin directory when its listing is available, or install this package from GitHub in clients that support repository plugins. Enable the Leash connection and sign in at lea.sh when prompted. Each installation receives a separate, revocable connection. Some hosts share one connection across multiple bots; Leash cannot distinguish bots that use the same credentials. Use separate connections where your host supports them. The shared endpoint is https://secure.lea.sh/mcp. Never append another person's token or put a personal link in a public package.
For Gemini CLI: gemini extensions install https://github.com/open-leash/leash-plugin. Run /mcp auth leash if sign-in is requested. For OpenClaw, use openclaw plugins install git:github.com/open-leash/[email protected], then inspect the enabled leash bundle. Its compatibility format is Cursor; no native code runs. For other clients, use their remote HTTP server option with the shared endpoint and OAuth. A public directory submission is not the same as an approved listing. Check the release notes for current availability.
Run the Leash setup skill or ask: "Check Leash is connected without accessing my personal accounts." Success must come from the check_connection tool, not merely from listing available tools. Then connect the accounts you want at https://lea.sh/personal.
This package includes a setup skill and a personal-account skill. Cursor loads a packaged rule and Gemini CLI loads GEMINI.md while the extension is enabled. A plugin cannot guarantee that all AI activity uses Leash. For a permanent preference in other clients, add the credential-free rule from GEMINI.md to the client's supported personal instructions. ChatGPT web uses Settings → Personalization → Custom instructions; Claude app uses Settings → General → Instructions for Claude; Cursor uses User Rules. A chat reply confirming the connection does not confirm that these settings were saved. Preserve your other instructions. Never add credentials to memory or shared files.
This integration uses personal Leash connections. The personal-connection retention terms apply to it; workspace and desktop-client retention terms describe the separate business service. Protection checks may process relevant request and response content with TypeSafe JEV. Audit history is retained for 90 days. When undo is enabled, supported recovery details are encrypted and retained for up to 7 days. Turning undo off stops new recovery capture. Read https://lea.sh/privacy for the full policy.
Disable or uninstall the plugin in your AI, remove any Leash-specific saved preference you added, then remove its connection in Your AIs at https://lea.sh/personal. Removing that connection revokes access immediately without disconnecting other AIs.
https://lea.sh/contact · [email protected]
Privacy: https://lea.sh/privacy · Terms: https://lea.sh/terms
This repository contains only public integration metadata, instructions and brand assets. Leash's gateway and protection engine remain private.
This repo does not document an install step we could read. Check the README on GitHub.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/leash to learn what the "Leash" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
This server doesn't publish a machine-readable tool manifest, and it doesn't expose a public endpoint we could ask. Connect the server locally to see what it exposes.
We could not run this server: it ships no npx package for our sandbox and no public endpoint. The four checks that need a live server are left out, and the grade tops out at B until one exists.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/leash)Nothing comparable is listed yet.
v1.0.3Leash 1.0.3Release notesv1.0.2Leash 1.0.2Release notesv1.0.1Leash 1.0.1Release notesv1.0.0Leash 1.0.0Release notesConnect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "leash" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.