Skip to content
MCP server

REA

CLI and MCP server that lets coding agents reverse engineer apps and binaries

Runs locallyActively maintainedStatus and history

The repository was last updated 6 hours ago and is published under MIT.

Pricing
Open source
Platforms
CLI, macOS, Windows
Runs
Locally
GitHub stars
464K
Last commit
today
Language
TypeScript

About REA

REA is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

REA is a command-line tool and MCP server that gives a coding agent the means to inspect software. You point your agent at an app, a game or a website and ask how a feature works.

The agent reads the program's code and observes what it does while running, then explains the behavior or helps rebuild it. The project's site walks through examples such as working out why Windows Calculator turns 200 + 10% into 220.

Setup is done with an npx command that shows a plan for approval before installing, then connects REA to the agent. It suits developers and researchers who want an agent to investigate how existing software behaves.

Install

Run in a terminal

claude mcp add rea -- npx -y rea-agents

Add to claude_desktop_config.json

{
  "mcpServers": {
    "rea": {
      "command": "npx",
      "args": [
        "-y",
        "rea-agents"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "rea": {
      "command": "npx",
      "args": [
        "-y",
        "rea-agents"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "rea": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "rea-agents"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "rea": {
      "command": "npx",
      "args": [
        "-y",
        "rea-agents"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "rea": {
      "command": "npx",
      "args": [
        "-y",
        "rea-agents"
      ]
    }
  }
}

What it does

Agent-driven inspection
Lets a coding agent read a program's code and watch its behavior while it runs.
CLI plus MCP server
The same tooling is reachable from a terminal or from an MCP-capable agent.
Guided setup
An npx setup command presents a plan for approval and then verifies the install.
Interactive examples
The site includes worked investigations, such as a calculator and a browser game, with guides.

Good for

  • Explain how a specific app feature works
  • Investigate binary behavior with an agent
  • Rebuild a feature from observed logic
  • Study browser or web app behavior
  • Learn reverse engineering through worked examples

Pricing

Open source

Open source (MIT)

Prices change. Check rea.tools before you buy.

REA FAQ

How do I install REA?

Run npx rea-agents@latest setup, approve the setup plan, then restart your agent.

Which license does it use?

The repository lists the MIT license.

What transport does the MCP server use?

The registry entry lists stdio.

Is REA free?

Yes. REA is open source, so you can use and self-host it for free.

How do I add REA to Claude Code?

Run this command in your terminal: claude mcp add rea -- npx -y rea-agents

What are the best alternatives to REA?

The closest alternatives to REA are Codebase Memory, GitHub, Serena MCP: the IDE for your agent, XERJ and Ouroboros.

Alternatives to REA

  1. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  2. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  3. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  4. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  5. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools
  6. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling