REA MCP APP: Reverse Engineer Anything

AI Software Engineer: Anthony Cavanaugh
Based on the original skill repository https://github.com/morluto/rea and extended with additional features and improvements.

One MCP App and CLI to uncover how software works—from native binaries and managed code to Electron apps, websites, and live runtime behavior.

See a feature you like. Understand how it works, down to the binary level.

Trace a behavior through code, events, and execution. REA turns local analysis into linked Evidence your agent can inspect, question, and use in a durable workspace to build a reconstruction, compare real behavior, and verify declared cases. Optional AI specialists investigate assigned Evidence and report back to your main agent; cloud reasoning stays off until you enable it.

Quick start · How REA works · What you can analyze · Showcases · FAQ · Documentation

npx rea-agents setup

See a feature in an app that you want in your own product? Ask your agent to investigate it with REA. It can inspect the app without its source code, explain how the feature works, show the evidence, and build a version for your project.

REA connects your agent to tools for inspecting native binaries, JavaScript and Electron apps, .NET assemblies, and websites. You can also use the same tools from your terminal. Analysis runs locally, and results include the evidence and limitations behind each conclusion.

The MCP App investigation workbench adds a color-coded Evidence workspace and an optional OpenRouter analyst/reviewer team. Both model IDs are explicitly configurable with no defaults. Cloud reasoning is disabled until enabled on the server; selected Evidence is sent to OpenRouter only for delegated assignments. The main agent receives reports through REA's start/read/cancel tools. The durable feature workspace connects selected behaviors, case timelines, executed comparisons, revisioned projects and portable handoffs. Finite verification and canonical readiness remain distinct results.

The workbench includes light/dark themes and portable fullscreen. Scoped specialists report to the main agent under shared request, token and spending limits; specialist mode remains optional. Windows Electron captures now use a retained native Job Object to clean up the launched application and descendants, and retain ownership when cleanup cannot be verified.

The acceptance and comparative benchmark report records real browser, managed-artifact and Electron checks plus 30 live coding trials. On this finite task, REA Evidence improved observed completion, while specialist reports hit their output limit and added overhead. These results do not establish general sub-agent superiority. Installed Codex App acceptance was removed from the final scope at the user's request.

Setup registers REA with your agent and installs matching workflow instructions. Native analysis can use an existing Hopper, Ghidra, or IDA installation; setup can optionally install Hopper with approval. Static JavaScript analysis needs no native analysis engine.

Visit the REA website for setup instructions, illustrated guides, and real case studies.

Quick start

Set up your agent

With Node.js and npm installed, run:

npx rea-agents setup

Choose your agents, review the proposed changes, and approve them. Setup adds REA's MCP server and matching workflow instructions, with backups of existing configuration. Restart your agent afterward.

Setup supports Claude Code, Codex, Cursor, Gemini CLI, Grok Build and other agents. See installation and setup for provider configuration and manual MCP registration.

Ask your agent

Understand how search works in the Notes app, show me the evidence, and build a
similar feature for my project.

Replace Notes with your target app and the feature you want to understand.

Use the terminal

Inspect an extracted JavaScript/Electron app directory or ASAR:

npx -y rea-agents@latest analyze-javascript-application /absolute/path/to/app --json

The result includes modules, imports, Electron boundaries and their evidence. Replace the path with your target, such as "D:/apps/example" on Windows.

To install the rea command for regular use:

npm install --global rea-agents
rea --help

For native analysis, configure a provider first. See the CLI and Evidence guide for native commands, provider selection, snapshots and scripting.

Update REA

REA changes quickly, and new releases include frequent bug fixes. Keep your installation up to date.

For an npm-installed CLI:

rea update

To refresh your agent registrations and skill, run the setup command printed by the update.

If you use npx, update your agent setup with:

npx rea-agents@latest setup

Review the setup changes and restart your agent. For one-off CLI commands, use npx rea-agents@latest followed by the command.

Connect from an MCP client manually

For clients that use the mcpServers JSON format, add REA to the client's MCP configuration file (often named mcp.json):

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

Save the file and restart or reconnect the client. This starts REA as a local stdio MCP server. Client-specific config locations and other formats are in the manual MCP registration guide; guided setup with npx rea-agents setup can write the matching registration for supported clients.

Open the REA MCP App

In a session connected to REA, ask your client to open the REA workbench or call rea_workbench. MCP Apps compatible clients render the interactive Evidence workspace; clients without MCP Apps support can still use REA's tools and receive their regular results. See the MCP App guide for the workbench features and optional OpenRouter configuration. REA does not load .env files automatically, so configure any optional server variables in the MCP client's server environment and keep credentials in its secret store.

Related MCP server: HexWitness

How REA works

Your agent calls REA through MCP to inspect the target and trace relevant code. REA returns findings with their evidence. The agent uses them to ask follow-up questions, explain the behavior, or write and test an implementation. CLI commands use the same workflows.

Open the full-size figure.

What you can analyze

REA requires Node.js 22.x (>=22.19), 24.x (>=24.11), or 26+, plus npm. Additional tools and host support depend on the target:

Static JavaScript and .NET inspection read the supplied files without running the application. Runtime capture runs or interacts with the selected target using your user permissions; each runtime guide describes its effects.

Native formats and host support vary by provider. See Hopper and Ghidra setup, the IDA guide, and experimental Windows Ghidra support. Ghidra also supports 16-bit DOS analysis. For large binaries, raise its startup deadline with REA_GHIDRA_STARTUP_TIMEOUT_MS. For provider selection, see the CLI guide. Check release availability for features added since the latest npm release.

Showcases

DX-Ball: reconstruct a sound-pan calculation

Follow a sound call into its position-to-pan helper, inspect the instructions, and turn incomplete pseudocode into C. The reconstruction passes 3,205 original-x86 cases and reproduces all 63 compiled function bytes.

Read the case study · Reconstruction repository

Notion: trace the Electron clipboard bridge

Find the renderer's clipboard API, follow it through preload and IPC into the main process, and inspect the rich clipboard format.

Read the case study

TH04: recover a DOS bullet-ring calculation

Inspect the original PC-98 game's 16-bit instructions, recover the fixed and aimed angle calculations, and compare the reconstructed C++ with the historical compiler output.

Read the case study · Reconstruction repository

If you've used REA on something interesting, we'd love to see it. Share your case in an issue or a pull request, including the target, your question, how REA helped, and what you found.

FAQ

Any agent that supports local MCP servers. Setup configures the supported agents; other clients can use manual MCP registration.

Deep native analysis uses one of them. Static JavaScript and .NET inspection work without a native analysis engine. Setup can install Hopper after approval; Ghidra and IDA use your existing installations. See provider setup.

REA starts Hopper when an operation needs it. On macOS, a first-run dialog may ask you to choose demo mode or activate your license. See Hopper startup and troubleshooting.

The skill supplies investigation instructions for your agent. Use npx rea-agents setup to register REA's MCP server and install the matching instructions, then restart your agent. See skill-only installation.

Native analysis returns pseudocode and assembly. JavaScript/Electron analysis recovers modules and their relationships. Your agent uses these findings to write and test an implementation; the showcases give worked examples.

REA analyzes targets locally. Your agent receives the tool results, and its model provider has its own data policy.

Update first; a recent release may already fix it.

For an npm-installed CLI:

rea update

For agent setup through npx:

npx rea-agents@latest setup

If you're using an agent, complete the setup refresh and restart it. Retry the same task. If the problem persists, open an issue with your REA version, target type, steps to reproduce and error output.

Documentation

Start with the website's worked guides. For exact options, prerequisites and result contracts:

• Installation and setup: agent registration, provider configuration, updates and uninstall.

• Readiness and troubleshooting: diagnose one agent or analysis engine.

• CLI and Evidence: commands, provider selection, snapshots, import/export and exit statuses.

• MCP contracts and agent prompts: tool results, sessions and guided investigations.

• Tool catalog: generated inventory of tools, providers and CLI commands.

• Roadmap: planned work and capability trackers.

Report vulnerabilities through SECURITY.md.

Disclaimer

REA provides tools for lawful reverse-engineering research, analysis, and reconstruction. You are responsible for obtaining any required authorization and complying with applicable laws. The project does not endorse illegal or unauthorized use.

REA is an open-source software project. We have not issued or endorsed any cryptocurrency or token. Tokens using the REA name are not affiliated with the project.

Contributing

We'd love your help with REA! Open an issue to report a bug or suggest a feature, or send a pull request to improve the code or docs.

See CONTRIBUTING.md for development setup and checks, testing for verification lanes, and the architecture map for the project structure.

License

MIT