Rea

This is an MCP server, not a DSH bundle. It is wired in through the official @deepseek-ai/dsh-mcp-client bridge: one plugin row in your config, pointing at either a stdio command or an http endpoint. Its tools then appear to the agent as mcp__rea__<tool>, the same naming Claude Code and Codex use.

{
  "name": "@deepseek-ai/dsh-mcp-client",
  "config": {
    "server": "rea",
    "command": "<stdio command from the README>",
    "url": "<or an http endpoint, if the server is remote>"
  }
}

Prerequisites

API key

Not required.

Network access

Not required at runtime.

Language

TypeScript

Verdict reason

mcp-server uses its own install path, so bundle checks do not apply

package.json read

package.json

Rules applied from

docs/user/develop/basic/publish.md

Checked at

2026-08-15

Install-time scripts

prepare, prepack

**English** · [简体中文](README_zh.md) · [日本語](README_ja.md) · [한국어](README_ko.md) · [العربية](README_ar.md) **See a feature you like. Understand how it works, down to the binary level.** See a feature in an app that you want in your own product? Give the app to your agent—even without its source code. With REA, the agent can investigate the feature, explain how it works, show its evidence, and build a version adapted to your stack and requirements. REA gives agents one consistent way to investigate software. Today that includes deep native analysis and function dossiers through Hopper or bring-your-own Ghidra on Linux, plus an experimental Windows x64 Ghidra P0 for approved native PE applications; execution-free managed PE/CLI triage; reproducible Evidence v2 records; controlled process captu