FastREA MCP server
Commit Oct 29, 2026Converts native binaries into clean C source code using headless Ghidra to assist LLMs with binary decompilation and reversing workflows.
Also known as 4B2A/FastREA
- Stars
- 1
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Oct 29, 2026
- License
- MIT
What is FastREA MCP?
FastREA converts native binaries into clean C source code using headless Ghidra to assist LLMs with binary decompilation and reversing workflows.
Summary generated from the project's README
About FastREA MCP server
Converting native binaries into clean C source code from within your AI assistant is the primary function of FastREA. This tool is designed for security researchers and reverse engineers who need to provide LLMs with readable code for analysis. By using a headless Ghidra implementation, the server allows models to decompile executables without the overhead of complex multi-agent loops or heavy dependencies.
To use this server, you must have Python 3.10+ and Ghidra installed on your local machine. The setup process involves running a setup.py script that automatically detects your Ghidra installation and configures your Claude Desktop or Cursor IDE settings. Once configured, the model uses the fastrea_analyze tool to orchestrate the decompilation process. The engine writes a Java script to boot Ghidra in headless mode, generates a C source file in the target directory, and streams that code back to the model context for immediate parsing.
What you can do with it
- 1Analyze binary protection routinesAsk the AI to examine a specific executable file to identify how it protects its code.
- 2Decompile executables to CInstruct the model to transform a native binary into readable C source code.
- 3Automate reverse engineering workflowsProvide an LLM with the ability to handle binary reversing tasks through a single tool.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachable4b2a/fastrea is public and reachablegithub.com/4b2a/fastrea ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-29github.com/4b2a/fastrea ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubFastREA ⚡
FastREA is an ultra-lightweight, zero-overhead Model Context Protocol (MCP) server for binary decompilation. Inspired by the core concepts of morluto/rea, it eliminates heavy multi-agent loops and complex dependencies. Instead, it provides your LLM with a single, laser-focused capability: Convert native binaries into clean C source code instantly using headless Ghidra.
🛠️ Architecture Overview
The system consists of only two files:
setup.py: A one-time initialization script that automatically scans your environment, detects Ghidra, and registers FastREA across your IDEs and Claude Desktop config files.main.py: The lightweight stateless MCP engine called by the model to orchestrate headless Ghidra execution and stream pure C output directly into the model context.
📦 Dependencies & Installation
FastREA relies on minimal external components. Ensure you have Python 3.10+ and Ghidra installed locally.
Required Python Libraries
To run the MCP engine, you must install the official Model Context Protocol Python SDK. Run the following command in your terminal:
pip install mcp
🚀 Quick Start
1. Provision Environment
Run the automated configuration script. It will automatically scan common paths for Ghidra and inject the FastREA integration directly into Claude Desktop and Cursor configurations:
python setup.py
2. Execution & Usage
Restart your Claude Desktop application or Cursor IDE. You can now prompt your model naturally to handle binary reversing workflows:
"Use fastrea to analyze the binary at
/absolute/path/to/target.exeand explain its primary protection routines."
🔄 Under the Hood Process:
- The model detects your instruction and triggers the
fastrea_analyzeMCP tool insidemain.py. main.pydynamically writes a clean Java decompile script and boots Ghidra in headless mode.- Ghidra exports a flat
target.exe_decompiled.csource file directly in the executable's directory. - FastREA reads the file contents and provides the structured code back to the LLM.
- The model parses the pristine raw C source code flawlessly without any context bloat.
📄 License
This project is open-source and licensed under the MIT License.
FastREA MCP questions
How do I install FastREA?
Run the automated configuration script using python setup.py, which scans for Ghidra and configures your IDEs.
How does the decompilation process work?
The server writes a Java decompile script, runs Ghidra in headless mode, and exports a C source file which is then read back to the LLM.