Rehe

Created By
anthropicsa year ago
Overview

what is Rehe?

Rehe is a framework for creating Desktop Extensions (DXT) that allows developers to package local MCP servers into zip archives for easy installation and distribution.

how to use Rehe?

To use Rehe, developers can create a DXT by organizing their MCP server files and a manifest.json into a zip file. The CLI tool provided in the repository simplifies this process.

key features of Rehe?

  • Single-click installation of local MCP servers.
  • CLI tool for creating DXT files and manifest.json.
  • Open-source specification for DXT, promoting a collaborative ecosystem.

use cases of Rehe?

  1. Distributing local MCP servers for AI applications.
  2. Simplifying the installation process for end users.
  3. Enabling developers to create and share extensions easily.

FAQ from Rehe?

  • What is a DXT?

A DXT is a zip archive containing a local MCP server and a manifest file that describes its capabilities.

  • How do I create a DXT?

Use the CLI tool provided in the repository to initialize and pack your local MCP server into a DXT.

  • Is Rehe open-source?

Yes! Rehe is open-sourced to encourage community contributions and collaboration.

Project Info
Created At
a year ago
Updated At
10 months ago
Author Name
anthropics
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

2 days ago
Tavily Mcp
@tavily-ai

JavaScript
a year ago